2017 IEEE Second International Conference on Data Science in Cyberspace (DSC) (2017)
Shenzhen, Guangdong, China
June 26, 2017 to June 29, 2017
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/DSC.2017.9
Recent advances in Intrusion Risk Assessment (IRA) have brought promising solutions to enhance Intrusion Response Systems (IRS). However, current researches lack reasonable solutions to exploit system state information. Without the system state, the IRA results may suffer from the high false rate of Intrusion Detection Systems (IDS). To address this limitation, we propose a novel State-Aware Risk Assessment Model (SRAM) by taking both the outputs of IDS and system state information into account. Specific evaluation factors are formulated for different attack types to improve the pertinence of evaluation. To better meet the needs of Quality of Service (QoS), expected weights on Confidentiality, Integrity and Availability (CIA) are considered based on different response intensions. D-S evidence theory is introduced in fusing the evaluation factors to provide an objective assessment. Experimental results show our approach can increase the credibility of IRA results effectively.
Risk management, Random access memory, Quality of service, Hidden Markov models, Indexes, Bandwidth, Security
F. Li, F. Xiong, C. Li, L. Yin, G. Shi and B. Tian, "SRAM: A State-Aware Risk Assessment Model for Intrusion Response," 2017 IEEE Second International Conference on Data Science in Cyberspace (DSC), Shenzhen, Guangdong, China, 2017, pp. 232-237.