Learning and Classification of Malware Behavior

Malicious software in form of Internet worms, computer viruses, and Trojan horses poses a major threat to the security of networked systems. The diversity and amount of its variants severely undermine the effectiveness of classical signature-based detection. Yet variants of malware families share typical behavioral patterns reflecting its origin and purpose. The paper aims to exploit these shared patterns for classification of malware and propose a method for learning and discrimination of malware behavior.