Why it matters
May 18, 2026 - May 21, 2026
The 47th IEEE Symposium on Security and Privacy and its workshops convened in San Francisco with a dedicated machine-learning security track and research on LLM privacy, alignment, jailbreaks, attacks, and defenses. The co-located Secure Agents for Generative AI workshop concentrated specifically on agent architectures and their security boundaries.
My takeaway: Use the proceedings to extract explicit attacker capabilities, system assumptions, datasets, and artifacts. Favor results evaluated against adaptive attacks and realistic tool or data access, and convert relevant papers into product-level tests rather than assuming model-only defenses secure an agent workflow.