Talks & News

Guest segment on evaluating agentic AI in security, and how organizations are cutting through 'AI fatigue' to make real decisions about deployment.

Talk introducing the five-level autonomy framework, evidence ladder, and three architectural foundations for evaluating earned autonomy in deployed AI systems.

Architectural deep-dive on tool scoping, platform-enforced authorization, prompt injection mitigation, and graduated oversight for production LLM agents.

Paper accepted at CAMLIS 2025 — an open-source benchmark and three metrics (detection accuracy, economic cost of syntactic correctness, robustness of query) for measuring LLM-generated security rules.

Sponsor interview on the rising use of spam bombing and email bombing as initial-access techniques in modern intrusion campaigns.