Bypassing Cylance's AI Malware Detection

Summary

Researchers at Skylight were able to create a universal bypass string that evades detection by Cylance's AI Malware detector when appended to a malicious file. Target: CylancePROTECT, Cylance Smart Antivirus Actor: Skylight Cyber Procedure: 1. The researchers read publicly available information about Cylance's AI Malware detector. They gathered this information from various sources such as public talks as well as patent submissions by Cylance. 2. The researchers had access to Cylance's AI-enabled malware detection software. 3. The researchers enabled verbose logging, which exposes the inner workings of the ML model, specifically around reputation scoring and model ensembling. 4. The researchers used the reputation scoring information to reverse engineer which attributes provided what level of positive or negative reputation. Along the way, they discovered a secondary model which was an override for the first model. Positive assessments from the second model overrode the decision of the core ML model. 5. Using this knowledge, the researchers fused attributes of known good files with malware to manually create adversarial malware. 6. Due to the secondary model overriding the primary, the researchers were effectively able to bypass the ML model.

Deployers

• CylancePROTECT, Cylance Smart Antivirus

Tags

• MITRE ATLAS
• AML.CS0003