Semantics-Aware Malware Detection by Mihai Christodorescu, Somesh Jha, Sanjit A. Seshia, Dawn Song, Randal E. Bryant
AUTHORS' DESCRIPTION
'We observe that certain malicious behaviors (such as decryption loops) appear in all variants of a certain malware. Based on this intuition, we gave a formal semantics for malware detection. We also presented a malware-detection algorithm that is sound with respect to our semantics. Experimental evaluation demonstrated that our algorithm can detect all variants of certain malware, has no false positives, and is resilient to obfuscation transformations generally used by hackers.' Read the full article
by Mihai Christodorescu, Somesh Jha, Sanjit A. Seshia, Dawn Song, Randal E. Bryant
AUTHORS' DESCRIPTION'We observe that certain malicious behaviors (such as decryption loops) appear in all variants of a certain malware. Based on this intuition, we gave a formal semantics for malware detection. We also presented a malware-detection algorithm that is sound with respect to our semantics. Experimental evaluation demonstrated that our algorithm can detect all variants of certain malware, has no false positives, and is resilient to obfuscation transformations generally used by hackers.'








