Why it matters
August 12, 2026 - August 14, 2026
The 35th USENIX Security Symposium brings peer-reviewed systems-security research to Baltimore, with an unusually deep 2026 AI program. Dedicated ML-security sessions cover real-world and indirect prompt injection, adaptive jailbreak attacks, agent memory and resource-abuse failures, LLM privacy and backdoors, and a systematization of agent attacks and defenses; proceedings are open access.
My takeaway: Use the program as a source of threat models and reproducible artifacts, not a list of mitigations to copy blindly. Compare each paper's attacker access, model and tool assumptions, baselines, adaptive evaluation, and deployment realism, then turn applicable attacks into local regression tests.