Intrusion detection in communication networks
View Patent ↗An intrusion detection arrangement for communication networks comprising a network activity observer configured to monitor network traffic by the related traffic elements, such as data packets, thereof and to establish traffic profiles relative to the monitored traffic elements, such as one profile per each monitored traffic element, a misuse detector configured to determine a first indication of a probability of the profiled traffic representing malicious activity through co-operation with a model repository comprising at least one model characterizing a known intrusion attack, an anomaly detector configured to determine, at least logically in parallel with the misuse detector, a second indication of a probability of the profiled traffic representing anomalous activity through cooperation with a model repository comprising at least one model characterizing legitimate network activity, and a classifier configured to operate on said first and second indications to generate a classification decision on the nature of the profiled traffic, wherein the applied classification space includes at least one class for legitimate traffic and at least one other class for other traffic such as malicious and/or anomalous traffic. A corresponding method is presented.
1. An intrusion detection arrangement for communication networks comprising
a network activity observer configured to monitor network traffic by the related traffic elements, optionally data packets, thereof and to establish traffic profiles relative to the monitored traffic elements, such as one profile per each monitored traffic element,
a misuse detector configured to determine a first numerical indication of a probability, between 0 and 1, of the profiled traffic representing malicious activity through cooperation with a model repository comprising at least one model characterizing a known intrusion attack,
an anomaly detector configured to determine, at least logically in parallel with the misuse detector, a second numerical indication of a probability, between 0 and 1, of the profiled traffic representing anomalous activity through co-operation with a model repository comprising at least one model characterizing legitimate network activity, and
a classifier configured to operate on said first and second numerical indications to generate a joint classification decision on the nature of the profiled traffic, wherein the applied classification space includes at least one class for legitimate traffic and at least one other class for other traffic such as malicious and/or anomalous traffic.
2. The arrangement of claim 1 , further comprising an alerter configured to provide an alert signal in response to a detected traffic of predetermined type, such as malicious and/or anomalous traffic.
3. The arrangement of claim 1 , wherein said misuse detector and/or anomaly detector is configured to cooperate with a first model associated with a traffic element, and with a second model associated with a plurality of traffic elements relating to a network activity pattern such as a predetermined intrusion scenario.
4. The arrangement of claim 1 , wherein said misuse detector and/or anomaly detector is configured to co-operate with a first model associated with a traffic element, and with a second model associated with a plurality of traffic elements relating to a network activity pattern such as a predetermined intrusion scenario, and wherein the first model applies XML (eXtensible Mark-up Language).
5. The arrangement of claim 1 , wherein said misuse detector and/or anomaly detector is configured to co-operate with a first model associated with a traffic element, and with a second model associated with a plurality of traffic elements relating to a network activity pattern such as a predetermined intrusion scenario, and wherein the second model applies MSC (Message Sequence Chart).
6. The arrangement of claim 1 , wherein the misuse detector is configured to compare the profiled traffic with modeled malicious network activity in order to determine the first numerical indication.
7. The arrangement of claim 1 , wherein the anomaly detector is configured to compare the profiled traffic with modeled legitimate network traffic in order to determine the second numerical indication.
8. The arrangement of claim 1 , wherein the classifier comprises decision logic configured to map, optionally through utilization of one or more threshold values, said first and second indications into said classification decision.
9. The arrangement of claim 1 , wherein the misuse detector is configured to determine the first numerical indication in the light of traffic element level, such as a data packet level, probability describing how malicious a monitored traffic element is and/or of network activity pattern level probability describing how malicious a monitored scenario relative to a plurality of traffic elements is.
10. The arrangement of claim 1 , wherein the anomaly detector is configured to determine the second numerical indication in the light of traffic element level, such as data packet level, probability describing how legitimate a monitored traffic element is and/or of network activity pattern level probability describing how legitimate a monitored scenario relative to a plurality of traffic elements is.
11. The arrangement of claim 1 , wherein said network activity observer is configured to monitor all said network traffic.
12. A method for intrusion detection relative to a communication network comprising
observing network traffic via monitoring the related traffic elements, optionally data packets, and establishing traffic profiles relative to the traffic elements, optionally one profile per each traffic element,
determining a first numerical indication, between 0 and 1, of a probability of the profiled network traffic representing malicious activity in view of one or more traffic elements through utilization of a number of models characterizing a number of known intrusion attacks,
determining, at least logically in parallel with the misuse detector, a second numerical indication, between 0 and 1, of a probability of the profiled network traffic representing anomalous activity in view of one or more traffic elements through utilization of a number of models characterizing legitimate network activity, and
classifying, jointly on the basis of said first and second numerical indications, the monitored and profiled traffic, wherein the applied classification space includes at least one class for legitimate traffic and at least one other class for other traffic such as malicious and/or anomalous traffic.
13. The method of claim 12 , further comprising generating an alert responsive to the classification decision.
14. A computer program product in a non-transitory computer readable storage medium for intrusion detection relative to a communication network, comprising program code for observing network traffic via monitoring the related traffic elements and establishing traffic profiles relative to the traffic elements, optionally one profile per each traffic element, determining a first numerical indication, between 0 and 1, of a probability of the profiled network traffic representing malicious activity in view of one or more traffic elements through utilization of a number of models characterizing a number of known intrusion attacks determining at least logically in parallel with the misuse detector a second numerical indication, between 0 and 1, of a probability of the profiled network traffic representing anomalous activity in view of one or more traffic elements through utilization of a number of models characterizing legitimate network activity, and classifying, jointly on the basis of said first and second numerical indications, the monitored and profiled traffic, wherein the applied classification space includes at least one class for legitimate traffic and at least one other class for other traffic such as malicious and/or anomalous traffic.