Florian Roth says years of low-quality YARA rules have trained AI models on bad practices like FP-prone rules, full-file hashes in conditions, and unnecessary regex.
Years of bad YARA rules published by the community and big vendors have finally paid off
AI models learned all the usual garbage
FP-prone rules never tested against even the smallest goodware set
full-file hash values in conditions
This finding is one of many signals tracked across Cyber Security. The live feed updates every few hours with new expert voices, debates, and emerging ideas.
← Back to Cyber Security