登入選單

返回Google圖書搜尋

An Adaptive Markov Game Model for Cyber Threat Intent Inference

Dan ShenErik BlaschGenshe ChenJose B. CruzKhanh Pham

出版	INTECH Open Access Publisher, 2009
URL	http://books.google.com.hk/books?id=D6PzoAEACAAJ&hl=&source=gbs_api

註釋

We implemented an adaptive Markov game theoretic situation awareness and adversary intent inference approach in a data-fusion/data-mining cyber attack and network defense framework (Fig. 2). The network security system was evaluated and protected from a perspective of data fusion and adaptive control. The goal of our approach was to examine the estimation of network states and projection of attack activities (similar to extended course of action (ECOA) in the warfare scenario). We used Markov game theory's ability to "step ahead" to infer possible adversary attack patterns. With the consideration that the parameters in each game player's cost function is not accessible to other players, we designed an adaptation scheme, based on the concept of Fictitious Play (FP), for the piecewise linearized Markov game model. A software tool was developed to demonstrate.