AGV semantic attack detection based on extended stochastic Petri net.

Semantic attack, as a covert and highly destructive network attack, seriously threatens the security of automatic guided vehicle (AGV) system. To make it worse, the dynamic change of wireless channel makes semantic attack detection more non-intractable. In order to solve the issues on the current semantic attack detection in wireless network environment, this paper proposes an extended stochastic Petri net (ESPN)-based detection method. It builds a stochastic Petri net (SPN) model for the normal operation process of AGV system, and detects the semantic attack by comparing the characteristics of relevance matrix, average dwell time and token density. Additionally, we innovatively add the wireless channel evaluation parameter in the SPN model, to estimate the current wireless channel state and eliminate the impact of wireless interference on attack detection. Eventually, an AGV attack detection system experimental platform has been developed to verify the effectiveness of the proposed method. The experimental results show that the proposed algorithm can effectively eliminate the impact of wireless channel interference on semantic attack detection, and has impressive detection performance.