Why it matters
December 7, 2026 - December 11, 2026
The Annual Computer Security Applications Conference brings applied security research to Los Angeles and includes four especially relevant workshops: agentic AI in offensive and defensive cyber operations, trustworthy machine learning, security and safety of AI in biotechnology, and AI for cyber-threat intelligence.
My takeaway: Treat the workshops as distinct evidence streams rather than one generic AI track. Compare offensive automation with containment and attribution controls, verify trustworthy-ML claims against explicit attackers, and apply stricter capability and consequence thresholds to biological and autonomous-security use cases.