Learning and classification of malware

Thorsten Holz and Carsten Willems, our partners in Sunbelt CWSandbox, have collaborated with Konrad Rieck, Patrick Dussel and Pavel Laskov on a paper, “Learning and Classification of Malware Behavior”.

The abstract explains it well:

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.

PDF link here (alternate).