Multi-stage attack detection using contextual information
conference contributionposted on 31.07.2018 by Kostas Kyriakopoulos, Francisco J. Aparicio-Navarro, Ibrahim Ghafir, Sangarapillai Lambotharan, Jonathon Chambers
Any type of content contributed to an academic conference, such as papers, presentations, lectures or proceedings.
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 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%.
This work was supported by the Engineering and Physical Sciences Research Council (EPSRC) Grant number EP/K014307/2 and the MOD University Defence Research Collaboration in Signal Processing, and by the British Council UK-Gulf Institutional Link Grant and the EPSRC Grant numbers EP/R006385/1 and EP/R006377/1.
- Mechanical, Electrical and Manufacturing Engineering