Multi-Stage Attack Detection Using Contextual Information


The appearance of new forms of cyber-threats, such as Multi-Stage Attacks (MSAs), creates new challenges to which Intrusion Detection Systems (IDSs) need to adapt. An MSA is launched in multiple sequential stages, which may not be malicious when implemented individually, making the detection of MSAs extremely challenging for most current IDSs. In this paper, we present a novel IDS that exploits contextual information in the form of Pattern-of-Life (PoL), and information related to expert judgment on the network behaviour. This IDS focuses on detecting an MSA, in real-time, without previous training process. The main goal of the MSA is to create a Point of Entry (PoE) to a target machine, which could be used as part of an Advanced Persistent Threat (APT) like attack. Our results verify that the use of contextual information improves the efficiency of our IDS by enhancing the detection rate of MSAs in real-time by 58%.



Contextual Information, Dempster-Shafer Theory, Fuzzy Cognitive Maps, Intrusion Detection System, Multi-Stage Attack, Network Security, Pattern-of-Life, Point of Entry


Aparicio-Navarro, F.J., Kyriakopoulos, K., Ghafir, I., Lambotharan, S., Chambers, J. (2018) Multi-Stage Attack Detection Using Contextual Information. IEEE/AFCEA Military Communications Conference MILCOM'18. Los Angeles, USA, October 2018.


Research Institute