WO2002099644A1 - Intrusion prevention system - Google Patents

Intrusion prevention system Download PDF

Info

Publication number
WO2002099644A1
WO2002099644A1 PCT/US2002/017602 US0217602W WO02099644A1 WO 2002099644 A1 WO2002099644 A1 WO 2002099644A1 US 0217602 W US0217602 W US 0217602W WO 02099644 A1 WO02099644 A1 WO 02099644A1
Authority
WO
WIPO (PCT)
Prior art keywords
assessment
activity
module
network
port
Prior art date
Application number
PCT/US2002/017602
Other languages
French (fr)
Inventor
Gary Manuel Jackson
Original Assignee
Psynapse Technologies, Llc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Psynapse Technologies, Llc filed Critical Psynapse Technologies, Llc
Publication of WO2002099644A1 publication Critical patent/WO2002099644A1/en

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L63/00Network architectures or network communication protocols for network security
    • H04L63/14Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
    • H04L63/1408Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic by monitoring network traffic

Definitions

  • the system simultaneously tracks all users who exhibit activity directed at priority-designated ports or services (i.e. e-mail or web traffic) as they enter and navigate through the network, as well as across-port activity.
  • the system assesses specific behavior and activity repeatedly and in real-time. Once a target for assessment is identified, the system then determines whether the network user navigating through a site intends to cause damage or conduct theft or does not intend to behave as an intruder.
  • the system is able to identify first-time attacks based on attack modifications in addition to more traditional known attacks. Finally, the system takes action when necessary to prevent intrusion damage.
  • Fig. 1 is a block diagram of the intrusion prevention system in accordance with an embodiment of the invention
  • Fig. 2 is a block diagram illustrating a sample port module in accordance with an embodiment of the invention
  • the packet activity analysis module 310 and activity translator module 320 within each specific port monitor work sequentially to first identify monitored activities and to then translate the activities to "present” and “absent” binary format.
  • the binary "present” and “absent” provide data from an input vector for the BPN assessment module 330.
  • the BPN or assessment module 330 produces an accurate rating within each session for the single to multiple activities exhibited by a user and presented to the BPN 330 as input for that time cycle. This assessment provides, in real-time, a determination of expertise and deception represented by the combination of activities, even if the combination had not been previously encountered.
  • the assessment results, as well as other specifics such as time, etc., are saved to a database.
  • his/her session data are sorted and filed in such a manner that the assessment information and associated data represent an intrusion profile for that specific intruder.
  • Such automatically generated profiles are used to check against active session data to assist in the determination that an identified intruder may be attempting access again by exhibiting similar patterns of activity, although a different source address may be used. It is assumed that although source identification may change, activity patterns represented by expertise and deception assessments, as well as supportive information such as time, etc. are more stable.

Abstract

Figure 1, the intrusion prevention system (105) includes a traffic sorter (130), an activity monitor (140), an inter-port fusion module (160), and an outcome director (165). The activity monitor (140) includes a cross-port module (142), a port Y intrusion prevention module (144), a port X intrusion prevention module (146) and an SMTP intrusion protection module (148). Data traffic arrives from the internet (120) and leaves the computer network. The external router (110) routes data traffic to and from the computer network and the Internet (120). A firewall (170), also coupled to the intrusion prevention system (105), provides a barrier between data traffic and end users of a network, or subnet. The firewall (170) is also coupled to an internal network (180). The interport fusion module (160) combines assessment results across the port monitors (142), (144), (146), and (148) when more than one port monitor is used at any given time to track session behavior (individual activity). The output from the outcome director (165) may be routed to either the tracking module (175), where the user's activities are tracked and the tracking module (175) has a tracking database (185), or to the firewall (170), where the instruction to block access is acted on.

Description

INTRUSION PREVENTION SYSTEM
BACKGROUND OF THE INVENTION
1. Field of the Invention
The invention relates to a computer network security system. More specifically, the invention provides a system and method allowing network access and proactively detecting and preventing unauthorized intrusion of the network based upon real-time assessment of behavior and intent.
2. Discussion of the Related Art
The development of network computing has allowed widely dispersed users to interact, communicate, and share resources via a computer network. The interconnected nature of networks makes them susceptible to intrusion by unauthorized users. Network intruders may range from innocent users who inadvertently gain access to information intended for delivery to another party to sophisticated and highly skilled intruders intending to access a secured site to inflict damage or perpetrate theft.
Conventional network intrusion detection systems can be divided into two different approaches: i.) pattern matching systems; and ii.) anomaly detection systems. Pattern matching systems operate by observing an intruder and looking for a set pattern based upon previous activity. Over time, through the observation of different intruders, a collection of patterns is compiled and may be used for broad-based detection of previously observed attacks. While this approach can provide broad protection against known or observed intrusion techniques, it does not protect against new intrusion techniques.
More recently, anomaly detection systems have been developed that generate statistical profiles of normal activity for a specific network or subnet. These profiles are usually generated via standard statistical methods or by self-adjusting neural networks that learn statistically
"normal" responding on a network. If a user appears outside of the "norm," then a warning may be issued or the user may be blocked. Non-normal activity may include any activity not falling within previously identified activity that is deemed allowable. Unfortunately, authorized users, as well as others who present no threat of damage or theft, can exhibit "non-normal" activity and can have access blocked or terminated, as well as intended intruders. Furthermore, because these past activity profiles are developed for a specific network, they cannot be carried over and incorporated into other networks. Both the conventional pattern matching and anomaly detection network security systems are based upon either capturing the past activity of intruders labeled as harmful or capturing the past activity of non-intrusion activity labeled as statistically normal. However, these systems are unable to proactively prevent intrusion damage created by first time attacks or even modifications of previous attacks. In general, the earlier an attack can be detected, the less overall damage it can cause to a victim.
SUMMARY OF THE INVENTION
As described above, conventional network security systems are reactive, whether based on pattern matching or anomaly detection methodologies, and do not provide effective protection against unknown and unfamiliar types of intrusions in an accurate manner (without raising the false positive and false negative rates). Thus, there is a need for a network security system that: proactively identifies network intruders; identifies unique first-time attacks based on attack modifications and traditional attacks; assists in identifying hackers by intent patterns who return to a site with a different source address; and responds to all attacks immediately to prevent further intrusion and damage.
Any system that is proactive and capable of identifying first time attacks must be able to anticipate that harmful activity is going to occur if actual damage is to be prevented. In other words, if a system is to be preventative in nature, intrusive damage or theft can be prevented only by anticipating its occurrence quickly enough for preventative measures to be taken. The invention provides a system and method for proactively assessing behavioral characteristics of users to determine the intent to conduct unauthorized intrusions into or within a computer network and responding appropriately to prevent theft or damage.
According to one embodiment of the invention, the system simultaneously tracks all users who exhibit activity directed at priority-designated ports or services (i.e. e-mail or web traffic) as they enter and navigate through the network, as well as across-port activity. The system then assesses specific behavior and activity repeatedly and in real-time. Once a target for assessment is identified, the system then determines whether the network user navigating through a site intends to cause damage or conduct theft or does not intend to behave as an intruder. The system is able to identify first-time attacks based on attack modifications in addition to more traditional known attacks. Finally, the system takes action when necessary to prevent intrusion damage.
Thus, it is an object of the invention to provide a network security system that proactively identifies network intruders. It is another object of the invention to provide a network security system that identifies unique first time attacks based upon attack modifications and traditional attacks.
It is another object of the invention to provide a network security system that assists in the identification of hackers by intent patterns who return to a site with different source addresses.
It is a further object of the invention to provide a network security system that responds to all attacks immediately to prevent further intrusion and damage.
In accordance with the objects outlined above, the invention provides a method for detecting unauthorized intrusion in a network that includes the steps of receiving packet level activity information from the network, sorting port specific activity information from the received packet level activity information, monitoring the port specific activity information and executing at least one of a blocking action or a tracking action based upon the monitored port specific activity information.
The invention further provides a system for protecting against unauthorized intrusion in a network system that includes a traffic sorter, an activity monitor, an inter-port fusion module and outcome director.
BRIEF DESCRIPTION OF THE DRAWINGS
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and, together with the description, serve to explain the principles of the invention. In the drawings:
Fig. 1 is a block diagram of the intrusion prevention system in accordance with an embodiment of the invention;
Fig. 2 is a block diagram illustrating a sample port module in accordance with an embodiment of the invention;
Fig. 3 is a block diagram of a back-propagation network (BPN) in accordance with the invention;
Fig. 4 is a two dimensional grid illustrating the neural network automated assessment ratings; and
Fig. 5 is a flowchart illustrating the process for identifying and blocking or tracking network activity in accordance with an embodiment of the invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
Reference will now be made in detail to the preferred embodiments of the invention, examples of which are illustrated in the drawings.
Fig. 1 is a block diagram providing an overview of a computer network, including an intrusion detection and prevention system 105 according to the invention. Fig. 1 shows a computer network coupled to a communications network 120, such as the Internet. However, it is important to note that the intrusion detection and prevention system in accordance with the invention may also be connected to any type of network using any underlying network protocols and is not limited to TCP/IP or Ethernet based networks.
The computer network includes an external router 110 coupled to a switch 115. The switch 115 is coupled to the intrusion prevention system 105 and to a firewall 170. The firewall 170 is also coupled to an internal network 180. The intrusion prevention system 105 is also coupled to a tracking module 175.
As shown in Fig. 1, the intrusion prevention system 105 includes a traffic sorter 130, an activity monitor 140, an inter-port fusion module 160, and an outcome director 165. In the embodiment of Fig. 1, the activity monitor 140 includes a cross-port module 142, a port Y intrusion prevention module 144, a port X intrusion prevention module 146 and an SMTP intrusion protection module 148. It is important to note, however, that the activity monitor 140 may include any number of dedicated port or activity monitors.
The intrusion prevention system 105 essentially acts as a sniffer on the network, gathering and processing a copy of all traffic going in and coming from the network. Assessment decisions formed by processing copied traffic are forwarded to either the existing firewall 170 or the external router 110, both of which are external to the intrusion prevention system 105.
Each of the monitors (the cross-port module 142, the port Y intrusion prevention module 144, the port X intrusion prevention module 146 and the SMTP intrusion prevention module 148) apply real-time automated assessment technology, as described in greater detail below, to process network activity and to differentiate intrusive from non-intrusive intent for respective targeted port activity.
In operation, data traffic arrives from the Internet 120 and leaves the computer network. The external router 110 routes data traffic to and from the computer network and the Internet 120. A firewall 170, also coupled to the intrusion prevention system 105, provides a barrier between data traffic and end users of a network, or subnet. As shown in Fig. 1, the external router 110 routes inbound data traffic from the Internet 120 to the switch 115. The switch 115 copies the inbound traffic, transferring the copied information to the traffic sorter 130. The traffic sorter 130 receives the copied data traffic and forwards the traffic to the appropriate port activity module within the activity monitor 140 . This directing function preprocesses and forwards port specific activity along with designated atomic level activity i.e, packet level activity, to the activity monitor 140. In general, the inbound data traffic is in the form of IP packets that are forwarded automatically by the external router 110 to the firewall 170 and are captured by the traffic sorter 130 in real time from the switch 115. The traffic sorter 130 uses layer 3 (network layer) and layer 4 (transport layer) header information to determine where to route the traffic. As will be described in greater detail below, the activity monitor 140 also carries out an assessment function, assessing the degree of intent to cause harm represented by a given user's activity.
The inter-port fusion module 160 combines assessment results across the port monitors 142, 144, 146 and 148 when more than one port monitor is used at any given time to track session behavior (individual activity). The inter-port fusion monitor 160, thus, generates a combined assessment and forwards a combined assessment result to an outcome director 165. The outcome director 165 outputs an instruction to block or track a user based upon combined assessment from the inter-port fusion monitor 160. The outcome director 165 is governed by a set of rules that determines whether a given assessment merits blocking or tracking. The outcome director 165 rules may be tuned to a given network so that the reaction to a given assessment can be varied.
The output from the outcome director 165 may be routed to either the tracking module 175, where the user's activities are tracked, or to the firewall 170, where the instruction to block access is acted on. The instruction to track a user is forwarded by the outcome director 165 to the tracking function 175, which serves as an evidence-gathering module. The determination to block or track a user with assessed harmful intent is pre-determined by a system administrator as a general default, or for a specific intruder. For example, if the need is to protect the network without exception, all intruders exhibiting assessed harmful activity will be blocked. If the purpose is to gather evidence on intruders (or a specific intruder), all relevant activity, including assessed intent, will be forwarded to a tracking module 175, where evidence of harmful intent and actual activity is gathered and stored. If activity at a current time cycle is not suspicious, it does not mean that an intrusion will not occur. Thus, while certain activity will not trigger a blocking or tracking action due to sub-threshold expertise and deception assessments, specified user activities will be continually tracked throughout a session and temporarily stored in the event that assessed threatening behavior occurs during subsequent time cycles later in the user's session.
One of the underlying principles of the intrusion prevention system 105 according to the invention is a recognition that a specific user's intent can change over time. Authorized traffic can quickly turn from authorized to unauthorized traffic or suspicious activity, which needs immediate attention to prevent damage to a targeted system. By constantly tracking all relevant port traffic by user, the intrusion prevention system 105 is capable of making assessment decisions in real time. Activity not targeted for the intrusion prevention system 105 detection is differentiated from the intrusion prevention system 105 targeted port activity by the traffic sorter 130 within the intrusion prevention system 105.
Fig. 2 shows a general port activity monitor module 200 in greater detail. It should be understood that while Fig. 2 shows a general port module 200, the discussion herein is equally applicable to any of the activity monitors discussed. As shown in Fig. 2, the sample port module includes a packet activity analysis module 210 coupled to an activity translator module 220 that is coupled to an assessment module 230. In operation, the packet activity analysis module 210 receives packet level information from the traffic sorter 130. The packet level analysis module 210 establishes a session for each user that is organized by source designation or activity. This is accomplished by processing layer 3 and layer 4 headers to pull out key information. Reassembly of packets is also accomplished to better determine activities to be monitored. Using the TCP sequence numbers, each session is monitored to track activities. With IP and UDP, more advanced methods incorporating the use of addresses, time, and other relevant information are used to differentiate activity of one user from the activity of another user. Activity is processed by parsing functions to identify designated port-specific activities to be monitored within the activity analysis module 210.
The activity translator module 220 receives input from parsers within the activity analysis module 210. The activity translator processes activity from a user and designates various activities as binary "1" if present and "0" if absent. For example, specific commands and activities used by an intruder and designated as activities to be tracked will be tracked and converted via a transducer function to a binary representation of the presence ("1") or absence ("0") of that activity in the activity translator module 220.
The activity translator module 220, as a centralized coordinating function, receives input from all transducer functions and forms a binary vector by user, which consists of a set of the combined l's and 0's that correspond to the presence and absence, respectively, of all monitored activities for a user at a set time cycle. This vector information is then forwarded to the assessment module 230. As is described in detail below, the assessment module 230 generates an assessment for a given user of the network based upon the binary input information provided by the activity translator module 220. The assessment module is trained to convert activity information into an assessment rating.
Fig 3 shows the functionality of the intrusion prevention system 105 in accordance with an embodiment of the invention. Fig. 3 shows a sample port activity monitor 300, a packet activity analysis module 310, an activity translator module 320 and a back propagation network assessment module 330. The sample port activity monitor 300 monitors pre-set activities, such as specific commands used by intruders. As shown in Fig. 3 for illustrative purposes, the sample port activity monitor observes six, or any number of activities: activity 1, activity 2, activity 3, activity 4, activity 5, to activity N. In practice, many scores of activities may be monitored, depending on the port that is monitored.
The packet activity analysis module 310 and activity translator module 320 within each specific port monitor work sequentially to first identify monitored activities and to then translate the activities to "present" and "absent" binary format. The binary "present" and "absent" provide data from an input vector for the BPN assessment module 330. The BPN or assessment module 330 produces an accurate rating within each session for the single to multiple activities exhibited by a user and presented to the BPN 330 as input for that time cycle. This assessment provides, in real-time, a determination of expertise and deception represented by the combination of activities, even if the combination had not been previously encountered. Unlike current commercial systems, the BPN 330 automated assessment within the intrusion prevention system 105 can make a reliable determination of intent represented by a combination of activities within a packet or series of packets that has not been previously encountered as a specific combination. The BPN 330 provides outputs 340 that are based upon all of the behavioral information monitored by the sample port activity monitor 300. The BPN 330 essentially considers each and every type of specified activity monitored and generates a profile of the monitored user. This profile indicates whether a user is exhibiting harmful intent and should be blocked or tracked based on options set. If a user is not judged to be exhibiting harmful intent, he is considered to be "non-harmful." The outputs 340 are ultimately directed to either a blocking function 350 or a tracking function 360 based on decision criteria established by the system administrator. The BPN is the foundation of the assessment module 330 The BPN is trained to recognize behavioral characteristics associated with each single monitored activity (antecedents) According to one embodiment of the invention, the BPN output may be represented as orthogonal X-Y coordinates formed by dimensions of deception and expertise In an embodiment in which more than 2 dimensions are used, such as the addition of persistence and accuracy to deception and expertise dimensions, a hyperdimensonal region determination rather than an X-Y coordinate decision space is created The assessment function is concluded with a categorization of the activity into one of several user intent classes determined by degree of deception and expertise present for that assessment cycle
Each "single" activity rating for each dimension of deception and expertise for this embodiment of the invention is determined by an expert panel trained in intrusion techniques, as well as information gained from the study of actual intrusions and from the current literature Whereas it is possible to determine dimension ratings for one single activity at a time along one dimension at a time, it is exceedingly difficult for human experts to rate multiple activities occurring simultaneously across more than one dimension Therefore, a methodology that can use single activity ratings along combined and orthogonal dimensions to produce accurate ratings for multiple activities, even if not previously encountered, is a hallmark of the intrusion prevention system neural network assessment function
More specifically, an input vector representative of behavior is processed by the trained BPN 330 with its output 340 designated as behavioral ratings across expertise and deception domains For any given input element, the BPN 330 returns an output indicating the degree of expertise and deception represented by the presence of that specific activity To be more precise, specific network activities are viewed as antecedents to intent that may be manifested as intrusion or non-intrusion behaviors Given the presence of a specific monitored activity, or combination of monitored activities, the BPN 330 returns an assessment and a determination of the intent and deception that are most likely associated with the activity The assessment functions are ultimately monitored by a blocking function 350 and a tracking function 360 within the outcome director 165 (depicted in Fig 1) The purpose of these functions is to forward respective block or track decisions to the firewall 170 or tracking module 175, respectively
Combinations of monitored activity across the BPN input layer return an overall accurate assessment of these characteristics, even if the combinations have not been previously encountered As a last step, the BPN ratings are superimposed on a conceptual grid whereby expertise and deception dimensions are orthogonal. The grid coordinates create four cells: high deception-high expertise (HD/HE), high deception- low expertise (HD LE), low deception-high expertise (LD/HE), and low deception-low expertise (LD/LE). Fig. 4 shows an example of a two dimensional grid in accordance with the invention. The grid provides a view of assessed behavior in an ongoing manner if a user's activity is selected for manual monitoring, or if activity from a user is selected for viewing automatically as a result of the user exhibiting suspicious behavior as defined by expertise and deception ratings of ongoing activity. Simultaneously, the BPN output, through the outcome director, is automatically monitored for decision determination by the blocking function 350 and the tracking function 360. The BPN ratings may be mapped in realtime using the grid shown in Fig. 4 so that a network administrator could monitor behavior over time.
The BPN 330 shown in Fig. 3 represents one of many possible BPNs. A single BPN monitors the activities of a specific user for specific port-related activity. Other BPNs assessing input data in real-time within designated port activity monitoring components operate in an identical manner. Each BPN input layer element corresponds to one monitored activity. The trained BPN on a time-cycled and repeated basis processes activity represented across the input layer. For example, in Fig. 3, for illustrative purposes, the input layer is represented by circled A, B and E input elements. This represents an input layer whereby these three multiple activities are active within a time cycle and have received designations of "1," while all other input elements representing an absence of activity have received a "0." It is important to note that, in practice, a single BPN may have scores of input elements representing scores of activities being monitored and converted to l's and 0's for BPN assessment.
The BPN process, which consists of receiving binary input and producing an assessment output, is almost instantaneous. This real-time process occurs for any single to multiple activities represented at the BPN's input layer for that particular time cycle. The assessment result takes the form of a scoring decision across four quadrants created by the intersection of dimensions of expertise and deception. For this particular example, the four quadrants are: high deception-high expertise [HD/HE], high deception- low expertise [HD/LE], low deception-high expertise (LD/HE), and low deception-low expertise [LD/LE]. Immediately following the determination of harmful intent, specific functions 350 and 360 process the BPN output to determine if each respective function should emit an active output instruction. In this example, if the assessment via the fusion module places the activity of the user into the high deception-high expertise category, the blocking function 350 will initiate an instruction to block the user from entry or will terminate the session. In cases where evidence gathering is required and set as an option (as opposed to blocking for HD/HE or LD/HD activity), the tracking function 360 will initiate a tracking instruction to the tracking module 175 to save the user activity to a special file and/or direct the user to a honeypot or similar function.
It is important to note that decision boundaries for tracking and blocking are distinct and allow maximum flexibility across these two decision areas via options that can be set by a system administrator. For example, options may be set to track users exhibiting behavior across the three quadrants not exhibiting the highest expertise and deception ratings and block all users whose activity reaches the upper right quadrant represented as high expertise and high deception. Any combination of tracking and blocking actions can be adjusted via quadrant thresholds. To illustrate with another example, the administrator may choose to not conduct tracking by setting tracking thresholds off and only block users whose activity reaches the high expertise and high deception quadrant. Actual disposition (e.g., block or track) is adjustable via threshold rules and can be determined by a system administrator to meet idiosyncratic security needs.
It is also important to note that regardless of tracking and blocking options, an individual user is tracked by session continuously until either the user is blocked (session terminated as a result of activity exceeding harmful intent thresholds) or the user terminates his connection. Continuous session monitoring is based on the premise that harmful intent may not be exhibited immediately by expert hackers and occur later in a session.
The assessment results, as well as other specifics such as time, etc., are saved to a database. In the event that a user is determined to be exhibiting harmful intent, his/her session data are sorted and filed in such a manner that the assessment information and associated data represent an intrusion profile for that specific intruder. Such automatically generated profiles are used to check against active session data to assist in the determination that an identified intruder may be attempting access again by exhibiting similar patterns of activity, although a different source address may be used. It is assumed that although source identification may change, activity patterns represented by expertise and deception assessments, as well as supportive information such as time, etc. are more stable.
The neural network pattern classification function is not limited to a BPN but may incorporate other neural network systems, as well as multidimensional statistical procedures. Likewise, the characteristics used for assessment are not limited to expertise and deception dimensions. Characteristics such as persistence and accuracy, among others, are useful as antecedent assessment dimensions, as well.
Fig. 5 illustrates the process for detecting and preventing unauthorized network intrusions in accordance with an embodiment of the invention. In Fig. 5, the process begins with step S510 wherein incoming traffic is received. The process then moves to step S520.
In step S520, the system uses information in the IP packets and port specific TCP and UDP packets to determine where to route the traffic. The process then moves to step S530.
In step S530, the system filters the routed information, establishes a session by user (source address), determines the presence or absence of specific monitored activity at the packet level and assigns the activity binary representations with a "1" indicating the presence of a specific monitored activity and a "0" indicating the absence of a specific monitored activity. The process then moves to step S540.
In step S540, the system conducts an assessment of the activity utilizing the assessment module or BPN as described above. The process then moves to step S550. In step S550, the system fuses the results from the assessment agent for respective port monitors if sessions are apparent across port monitors. If no other sessions have been established, then the assessment for the single port monitor proceeds and no combining of results is needed. The process then moves to step S560 and S580 simultaneously.
In step S560, the system determines whether the activity should be tracked based on tracking thresholds and in step S580 the system determines if the user's access should be blocked based on blocking thresholds. Blocking or tracking is mutually exclusive and established by adjustable thresholds by a system administrator. If in either steps S560 or S580, the system determines that the activity should not be tracked or blocked, then the process moves to step S595 and continues until such time that the user terminates the session him or herself or until the user's activity becomes threatening. If in step S560 the system determines that the activity should be tracked, the process moves to step S570.
In step S570, the system stores the tracking related information as a means to establish evidence of intrusive behavior in a specialized tracking database. If in step 580 it was determined that the user's access should be terminated, the process moves to S590. In step S590, the system initiates a blocking instruction to the firewall 170, all information is stored in a blocking database, and the intruder's connection is terminated automatically. From step S595, the process moves to step S597 where the process stores the session information in a session storage database.
It is important to make distinctions among three database functions. First, a session database may be provided whereby a user's activities and ratings are stored to allow tracking of expertise and deception repeatedly for the duration of a session. Second, a tracking database may be provided whereby specialized evidence gathering data based on transferred session data are stored and which may be used to provide "proof of a specific intruder's activities once a tracking decision has been made. Third, a blocking database may be provided that stores all relevant information generated in the session database that provides the sequence of events and ratings leading to the loss of access for a user. Unless an automated decision based on tracking or blocking criteria is made to store session and related data or unless the system administrator wishes to store expertise and deception profiles of non-harmful users, the session database is cleared for a user when the user exits the network.
While specific embodiments of the invention have been described herein, it will be apparent to those skilled in the art that various modifications may be made without departing from the spirit and scope of the invention.

Claims

Claims:
1. A method for detecting unauthorized intrusion in a network system, comprising the steps of: receiving packet level activity information from the network; sorting port specific activity information from the received packet level activity information; monitoring the port specific activity information; and executing at least one of a blocking action or a tracking action based upon the monitored port specific activity information.
2. The method according to claim 1, wherein the step of monitoring includes: identifying presence of at least one activity from the port specific activity information; assigning a binary representation (1 = present, 0=absent) to the at least one identified activity; and generating an assessment based upon the binary rating
3. The method according to claim 2, wherein the step of generating an assessment includes associating the binary rating with an assessment based upon predetermined behavioral criteria.
4. The method according to claim 3, wherein the step of generating an assessment includes mapping the assessment on at least one two-dimensional grid.
5. The method according to claim 4, wherein the step of mapping occurs dynamically and in real-time.
6. The method according to claim 2, wherein the step of generating an assessment includes generating a profile of user based upon the monitored port specific activity information.
7. The method according to claim 2, wherein the step of generating an assessment is carried out utilizing a back propagation network.
8. The method according to claim 7 wherein the back propagation network includes psychological assessment information.
9. The method according to claim 2, wherein the assessment is one of high deception/high expertise, high deception/low expertise, low deception/high expertise and low deception/low expertise.
10. The method according to claim 1, wherein the blocking action includes sending a blocking command to a firewall for blocking further network access.
11. The method according to claim 1, wherein the tracking action includes storing activity information in a tracking module.
12. A system for preventing unauthorized intrusion in a network system, comprising: a traffic sorter; an activity monitor operatively coupled to the traffic sorter; an inter-port fusion module operatively coupled to the activity monitor; and an outcome director operatively coupled to the inter-port fusion monitor.
13. The system according to claim 12, wherein the activity monitor includes at least one dedicated port monitor.
14. The system according to claim 13, wherein, the at least one dedicated port monitor includes a packet level analysis module, an activity translator module and an assessment module.
15. The system according to claim 14, wherein the assessment module includes a back propagation network.
16. The system according to claim 15, wherein the back propagation network includes psychological assessment information.
17. The system according to claim 14, wherein the traffic sorter receives packet level activity information from the network and sorts the port specific activity information from the network.
18. The system according to claim 14, wherein the activity monitor monitors the port specific activity information.
19. The system according to claim 14, wherein the activity translator module assigns a binary rating based upon presence (1) or absence (0) of at least one activity detected by the packet level analysis module.
20. The system according to claim 19, wherein the assessment module generates an assessment result based upon the binary rating.
21. The system according to claim 19, wherein the assessment module maps the assessment result utilizing at least one of a two dimensional grid or X dimensional grid for optional real-time viewing of a user's intent.
22. The system according to claim 20, wherein an outcome director initiates at least one of a blocking command or a tracking command based upon the assessment result.
23. The system according to claim 22, wherein the blocking command is directed to a system firewall. 24 The system according to claim 23 in which a blocking command results in the storage of all session data indicating all user activity and intent until such time as access is terminated
25 The system according to claim 22, wherein the tracking command is directed to a tracking module
26 The system according to claim 24, wherein the tracking module includes a tracking database for storing activity information that may be used to provide evidence of an intruder's harmful intent activities and at least one intent assessment during a session
27 The system according to claim 26, wherein the tracking database includes neural network assessment and associated information for the intruder that is at least one of tracked or blocked
28 The system according to claim 27, wherein the tracking database includes a comparison module for comparing the neural network assessment and associated information against a second assessment based upon a second network intrusion
29 The system according to claim 28, wherein at least one of a blocking or tracking action is executed based upon an output from the comparison module
30 A system for detecting unauthorized intrusion in a network system, comprising sorting means for sorting port specific activity from incoming packet level activity, monitoring means operatively coupled to the sorting means for monitoring the sorted port specific activity, and assessing means operatively coupled to the monitoring means for generating an assessment
31 A computer program product, comprising a computer usable medium having computer readable code embodied therein for preventing unauthorized intrusion into a computer network, the computer program product comprising computer readable program code configured to cause the computer to sort port specific activity information from packet level activity information received by the computer network, computer readable program code configured to cause the computer to monitor port specific activity information, and computer readable program code configured to cause the computer to execute at least one of a blocking action or a tracking action based upon the monitored port specific activity information
PCT/US2002/017602 2001-06-06 2002-06-05 Intrusion prevention system WO2002099644A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US09/874,292 US7458094B2 (en) 2001-06-06 2001-06-06 Intrusion prevention system
US09/874,292 2001-06-06

Publications (1)

Publication Number Publication Date
WO2002099644A1 true WO2002099644A1 (en) 2002-12-12

Family

ID=25363424

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2002/017602 WO2002099644A1 (en) 2001-06-06 2002-06-05 Intrusion prevention system

Country Status (2)

Country Link
US (1) US7458094B2 (en)
WO (1) WO2002099644A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2003094418A1 (en) * 2002-04-30 2003-11-13 Intelliguard I.T. Pty Ltd A.C.N. 098 700 344 A packet filtering system

Families Citing this family (80)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040073617A1 (en) 2000-06-19 2004-04-15 Milliken Walter Clark Hash-based systems and methods for detecting and preventing transmission of unwanted e-mail
US9525696B2 (en) 2000-09-25 2016-12-20 Blue Coat Systems, Inc. Systems and methods for processing data flows
US20110213869A1 (en) * 2000-09-25 2011-09-01 Yevgeny Korsunsky Processing data flows with a data flow processor
US20100042565A1 (en) * 2000-09-25 2010-02-18 Crossbeam Systems, Inc. Mezzazine in-depth data analysis facility
US8010469B2 (en) * 2000-09-25 2011-08-30 Crossbeam Systems, Inc. Systems and methods for processing data flows
US20110219035A1 (en) * 2000-09-25 2011-09-08 Yevgeny Korsunsky Database security via data flow processing
US20110238855A1 (en) * 2000-09-25 2011-09-29 Yevgeny Korsunsky Processing data flows with a data flow processor
US9800608B2 (en) * 2000-09-25 2017-10-24 Symantec Corporation Processing data flows with a data flow processor
US20110214157A1 (en) * 2000-09-25 2011-09-01 Yevgeny Korsunsky Securing a network with data flow processing
US20110231564A1 (en) * 2000-09-25 2011-09-22 Yevgeny Korsunsky Processing data flows with a data flow processor
EP1280298A1 (en) * 2001-07-26 2003-01-29 BRITISH TELECOMMUNICATIONS public limited company Method and apparatus of detecting network activity
KR100422802B1 (en) * 2001-09-05 2004-03-12 한국전자통신연구원 Security System against intrusion among networks and the method
US20030105881A1 (en) * 2001-12-03 2003-06-05 Symons Julie Anna Method for detecting and preventing intrusion in a virtually-wired switching fabric
US8578480B2 (en) 2002-03-08 2013-11-05 Mcafee, Inc. Systems and methods for identifying potentially malicious messages
US7693947B2 (en) 2002-03-08 2010-04-06 Mcafee, Inc. Systems and methods for graphically displaying messaging traffic
US7694128B2 (en) 2002-03-08 2010-04-06 Mcafee, Inc. Systems and methods for secure communication delivery
US8561167B2 (en) 2002-03-08 2013-10-15 Mcafee, Inc. Web reputation scoring
US7096498B2 (en) 2002-03-08 2006-08-22 Cipher Trust, Inc. Systems and methods for message threat management
US8132250B2 (en) 2002-03-08 2012-03-06 Mcafee, Inc. Message profiling systems and methods
US20060015942A1 (en) 2002-03-08 2006-01-19 Ciphertrust, Inc. Systems and methods for classification of messaging entities
US7870203B2 (en) 2002-03-08 2011-01-11 Mcafee, Inc. Methods and systems for exposing messaging reputation to an end user
US7124438B2 (en) 2002-03-08 2006-10-17 Ciphertrust, Inc. Systems and methods for anomaly detection in patterns of monitored communications
US7903549B2 (en) 2002-03-08 2011-03-08 Secure Computing Corporation Content-based policy compliance systems and methods
EP1527592A1 (en) * 2002-08-07 2005-05-04 British Telecommunications Public Limited Company Server for sending electronics messages
US7316031B2 (en) * 2002-09-06 2008-01-01 Capital One Financial Corporation System and method for remotely monitoring wireless networks
US8225407B1 (en) 2003-08-21 2012-07-17 Symantec Corporation Incident prioritization and adaptive response recommendations
US20050193429A1 (en) * 2004-01-23 2005-09-01 The Barrier Group Integrated data traffic monitoring system
US7895448B1 (en) * 2004-02-18 2011-02-22 Symantec Corporation Risk profiling
US20050188221A1 (en) * 2004-02-24 2005-08-25 Covelight Systems, Inc. Methods, systems and computer program products for monitoring a server application
US20050188080A1 (en) * 2004-02-24 2005-08-25 Covelight Systems, Inc. Methods, systems and computer program products for monitoring user access for a server application
US7373524B2 (en) * 2004-02-24 2008-05-13 Covelight Systems, Inc. Methods, systems and computer program products for monitoring user behavior for a server application
US20050188222A1 (en) * 2004-02-24 2005-08-25 Covelight Systems, Inc. Methods, systems and computer program products for monitoring user login activity for a server application
US20050187934A1 (en) * 2004-02-24 2005-08-25 Covelight Systems, Inc. Methods, systems and computer program products for geography and time monitoring of a server application user
US9154511B1 (en) 2004-07-13 2015-10-06 Dell Software Inc. Time zero detection of infectious messages
US7343624B1 (en) 2004-07-13 2008-03-11 Sonicwall, Inc. Managing infectious messages as identified by an attachment
WO2006039208A2 (en) * 2004-09-22 2006-04-13 Cyberdefender Corporation Threat protection network
US8635690B2 (en) 2004-11-05 2014-01-21 Mcafee, Inc. Reputation based message processing
US9323922B2 (en) * 2005-01-06 2016-04-26 Oracle International Corporation Dynamically differentiating service in a database based on a security profile of a user
US7573833B2 (en) 2005-04-21 2009-08-11 Cisco Technology, Inc. Network presence status from network activity
US7937480B2 (en) 2005-06-02 2011-05-03 Mcafee, Inc. Aggregation of reputation data
US7908357B2 (en) * 2005-09-21 2011-03-15 Battelle Memorial Institute Methods and systems for detecting abnormal digital traffic
US8170020B2 (en) * 2005-12-08 2012-05-01 Microsoft Corporation Leveraging active firewalls for network intrusion detection and retardation of attack
US7543055B2 (en) * 2006-06-20 2009-06-02 Earthlink Service provider based network threat prevention
US8281392B2 (en) 2006-08-11 2012-10-02 Airdefense, Inc. Methods and systems for wired equivalent privacy and Wi-Fi protected access protection
US7954143B2 (en) * 2006-11-13 2011-05-31 At&T Intellectual Property I, Lp Methods, network services, and computer program products for dynamically assigning users to firewall policy groups
US7954158B2 (en) 2006-12-19 2011-05-31 International Business Machines Corporation Characterizing computer attackers
US8763114B2 (en) 2007-01-24 2014-06-24 Mcafee, Inc. Detecting image spam
US8214497B2 (en) 2007-01-24 2012-07-03 Mcafee, Inc. Multi-dimensional reputation scoring
US8179798B2 (en) 2007-01-24 2012-05-15 Mcafee, Inc. Reputation based connection throttling
US7949716B2 (en) 2007-01-24 2011-05-24 Mcafee, Inc. Correlation and analysis of entity attributes
US7779156B2 (en) 2007-01-24 2010-08-17 Mcafee, Inc. Reputation based load balancing
US8955105B2 (en) * 2007-03-14 2015-02-10 Microsoft Corporation Endpoint enabled for enterprise security assessment sharing
US8959568B2 (en) * 2007-03-14 2015-02-17 Microsoft Corporation Enterprise security assessment sharing
US8413247B2 (en) * 2007-03-14 2013-04-02 Microsoft Corporation Adaptive data collection for root-cause analysis and intrusion detection
US20080229419A1 (en) * 2007-03-16 2008-09-18 Microsoft Corporation Automated identification of firewall malware scanner deficiencies
WO2008135822A2 (en) * 2007-05-03 2008-11-13 Telefonaktiebolaget Lm Ericsson (Publ) System and method for intrusion detection for communication networks utilizing signaling compression
US8086461B2 (en) * 2007-06-13 2011-12-27 At&T Intellectual Property Ii, L.P. System and method for tracking persons of interest via voiceprint
EP2023572B1 (en) * 2007-08-08 2017-12-06 Oracle International Corporation Method, computer program and apparatus for controlling access to a computer resource and obtaining a baseline therefor
US8185930B2 (en) 2007-11-06 2012-05-22 Mcafee, Inc. Adjusting filter or classification control settings
US8045458B2 (en) 2007-11-08 2011-10-25 Mcafee, Inc. Prioritizing network traffic
US8667582B2 (en) * 2007-12-10 2014-03-04 Mcafee, Inc. System, method, and computer program product for directing predetermined network traffic to a honeypot
US8160975B2 (en) 2008-01-25 2012-04-17 Mcafee, Inc. Granular support vector machine with random granularity
US8589503B2 (en) 2008-04-04 2013-11-19 Mcafee, Inc. Prioritizing network traffic
US8490171B2 (en) * 2008-07-14 2013-07-16 Tufin Software Technologies Ltd. Method of configuring a security gateway and system thereof
WO2010084344A1 (en) 2009-01-20 2010-07-29 Secerno Ltd Method, computer program and apparatus for analysing symbols in a computer system
US8234582B1 (en) 2009-02-03 2012-07-31 Amazon Technologies, Inc. Visualizing object behavior
US8250473B1 (en) 2009-02-03 2012-08-21 Amazon Technoloies, Inc. Visualizing object behavior
US8341540B1 (en) * 2009-02-03 2012-12-25 Amazon Technologies, Inc. Visualizing object behavior
US8954725B2 (en) * 2009-05-08 2015-02-10 Microsoft Technology Licensing, Llc Sanitization of packets
WO2011002818A1 (en) * 2009-06-29 2011-01-06 Cyberdefender Corporation Systems and methods for operating an anti-malware network on a cloud computing platform
US8666731B2 (en) * 2009-09-22 2014-03-04 Oracle International Corporation Method, a computer program and apparatus for processing a computer message
US8866347B2 (en) 2010-01-15 2014-10-21 Idex Asa Biometric image sensing
CN102812431A (en) 2010-03-22 2012-12-05 Lrdc系统有限公司 A method of identifying and protecting the integrity of a set of source data
US8621638B2 (en) 2010-05-14 2013-12-31 Mcafee, Inc. Systems and methods for classification of messaging entities
US9002755B2 (en) * 2013-02-05 2015-04-07 scenarioDNA System and method for culture mapping
US9363281B1 (en) * 2014-01-24 2016-06-07 Amazon Technologies, Inc. Detecting covert routing
PL3095034T3 (en) 2014-10-21 2019-11-29 Ironnet Cybersecurity Inc Cybersecurity system
WO2017189587A1 (en) * 2016-04-26 2017-11-02 Acalvio Technologies, Inc. Threat engagement and deception escalation
LT3338205T (en) 2016-07-14 2019-06-25 IronNet Cybersecurity, Inc. Simulation and virtual reality based cyber behavioral system
US10581859B2 (en) 2017-08-07 2020-03-03 International Business Machines Corporation Detection and prevention of attempts to access sensitive information in real-time

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5155801A (en) * 1990-10-09 1992-10-13 Hughes Aircraft Company Clustered neural networks
US5311593A (en) * 1992-05-13 1994-05-10 Chipcom Corporation Security system for a network concentrator
US5559883A (en) * 1993-08-19 1996-09-24 Chipcom Corporation Method and apparatus for secure data packet bus communication

Family Cites Families (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5311683A (en) * 1986-06-13 1994-05-17 Foundation Technology Limited Propulsion apparatus
EP1035699B1 (en) * 1993-01-20 2005-03-16 Koninklijke Philips Electronics N.V. Method for isolating a block frequency from a block formatted signal
US5991881A (en) * 1996-11-08 1999-11-23 Harris Corporation Network surveillance system
CA2276526A1 (en) * 1997-01-03 1998-07-09 Telecommunications Research Laboratories Method for real-time traffic analysis on packet networks
US6324656B1 (en) * 1998-06-30 2001-11-27 Cisco Technology, Inc. System and method for rules-driven multi-phase network vulnerability assessment
US6134664A (en) * 1998-07-06 2000-10-17 Prc Inc. Method and system for reducing the volume of audit data and normalizing the audit data received from heterogeneous sources
US6839850B1 (en) * 1999-03-04 2005-01-04 Prc, Inc. Method and system for detecting intrusion into and misuse of a data processing system
US6405318B1 (en) * 1999-03-12 2002-06-11 Psionic Software, Inc. Intrusion detection system
US6647400B1 (en) * 1999-08-30 2003-11-11 Symantec Corporation System and method for analyzing filesystems to detect intrusions
US6971028B1 (en) * 1999-08-30 2005-11-29 Symantec Corporation System and method for tracking the source of a computer attack
US6735702B1 (en) * 1999-08-31 2004-05-11 Intel Corporation Method and system for diagnosing network intrusion
US6671811B1 (en) * 1999-10-25 2003-12-30 Visa Internation Service Association Features generation for use in computer network intrusion detection
US6769066B1 (en) * 1999-10-25 2004-07-27 Visa International Service Association Method and apparatus for training a neural network model for use in computer network intrusion detection
US6519703B1 (en) * 2000-04-14 2003-02-11 James B. Joyce Methods and apparatus for heuristic firewall
US7707305B2 (en) * 2000-10-17 2010-04-27 Cisco Technology, Inc. Methods and apparatus for protecting against overload conditions on nodes of a distributed network
US7290283B2 (en) * 2001-01-31 2007-10-30 Lancope, Inc. Network port profiling

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5155801A (en) * 1990-10-09 1992-10-13 Hughes Aircraft Company Clustered neural networks
US5311593A (en) * 1992-05-13 1994-05-10 Chipcom Corporation Security system for a network concentrator
US5559883A (en) * 1993-08-19 1996-09-24 Chipcom Corporation Method and apparatus for secure data packet bus communication

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2003094418A1 (en) * 2002-04-30 2003-11-13 Intelliguard I.T. Pty Ltd A.C.N. 098 700 344 A packet filtering system

Also Published As

Publication number Publication date
US7458094B2 (en) 2008-11-25
US20020188864A1 (en) 2002-12-12

Similar Documents

Publication Publication Date Title
US7458094B2 (en) Intrusion prevention system
Dong et al. DDoS attack detection method based on improved KNN with the degree of DDoS attack in software-defined networks
US20010052014A1 (en) Systems and methods for distributed network protection
Tayyab et al. ICMPv6-based DoS and DDoS attacks detection using machine learning techniques, open challenges, and blockchain applicability: A review
US20070168532A1 (en) Systems and methods for distributed network protection
Scaranti et al. Artificial immune systems and fuzzy logic to detect flooding attacks in software-defined networks
Lysenko et al. DNS-based anti-evasion technique for botnets detection
Akbar et al. Intrusion detection system methodologies based on data analysis
CN111970300A (en) Network intrusion prevention system based on behavior inspection
Buragohain et al. Anomaly based DDoS attack detection
Song et al. Flow-based statistical aggregation schemes for network anomaly detection
BACHAR et al. Towards a behavioral network intrusion detection system based on the SVM model
Haggerty et al. Early detection and prevention of denial-of-service attacks: a novel mechanism with propagated traced-back attack blocking
CN116827690A (en) DDoS attack and cloud WAF defense method based on distribution type
SMADI et al. Application layer denial of services attack detection based on stacknet
Golovko et al. Intrusion recognition using neural networks
WO2001093531A2 (en) Systems and methods for distributed network protection
Hwoij et al. Detecting Network Anomalies using Rule-based machine learning within SNMP-MIB dataset
Kumar et al. Intrusion detection using soft computing techniques
CN115225301B (en) Hybrid intrusion detection method and system based on D-S evidence theory
CN114978667A (en) SDN network DDoS attack detection method based on graph neural network
KR20190050521A (en) Apparatus and method for detecting anomalous signs using profiling-based machine learning
Han et al. Effective discovery of attacks using entropy of packet dynamics
Mishra et al. Artificial intelligent firewall
Xiang et al. Protecting information infrastructure from ddos attacks by madf

Legal Events

Date Code Title Description
AK Designated states

Kind code of ref document: A1

Designated state(s): AE AG AL AM AT AU AZ BA BB BG BR BY BZ CA CH CN CO CR CU CZ DE DK DM DZ EC EE ES FI GB GD GE GH GM HR HU ID IL IN IS JP KE KG KP KR KZ LC LK LR LS LT LU LV MA MD MG MK MN MW MX MZ NO NZ OM PH PL PT RO RU SD SE SG SI SK SL TJ TM TN TR TT TZ UA UG UZ VN YU ZA ZM ZW

AL Designated countries for regional patents

Kind code of ref document: A1

Designated state(s): GH GM KE LS MW MZ SD SL SZ TZ UG ZM ZW AM AZ BY KG KZ MD RU TJ TM AT BE CH CY DE DK ES FI FR GB GR IE IT LU MC NL PT SE TR BF BJ CF CG CI CM GA GN GQ GW ML MR NE SN TD TG

121 Ep: the epo has been informed by wipo that ep was designated in this application
DFPE Request for preliminary examination filed prior to expiration of 19th month from priority date (pct application filed before 20040101)
REG Reference to national code

Ref country code: DE

Ref legal event code: 8642

122 Ep: pct application non-entry in european phase
NENP Non-entry into the national phase

Ref country code: JP

WWW Wipo information: withdrawn in national office

Country of ref document: JP