Program Behavior Fusion to Identify Malware

Due to the underground economy stimulation, malware creators are writing malicious codes at an alarming rate. at the same time, novel resistance techniques are commonly available, leading to a huge number of variants. Behavior-based detection techniques are a promising solution to this serious problem. in this paper we propose fuse program behaviors to identify malware. This approach uses Bayesian training to get the malicious degree of program behavior, adopt D-S synthesize rule to fuse program behaviors to detect virus. Our experimental evaluation shows that our prototype system effective on detecting malicious codes and their variants.