New malware detection system using metric-based method and hybrid genetic algorithm
Jinhyun Kim, Byung-Ro Moon · 2012
Malicious software, or malware for short, is one of the most serious threats to computer systems. Malware disguise techniques are becoming more sophisticated, and signature-based malware detection systems can not cope with disguised malware timely. In this paper, we propose a new approach to detect disguised malware, focusing on the malware scripts. The proposed system consists of a metric-based detection algorithm and a hybrid genetic algorithm. The genetic algorithm tries further detection by extracting the main core of a program. Experimental tests on the proposed system show a remarkable performance improvement over existing anti-virus programs.