Research & Notes
Cross-session threats, dynamic agent identity, trajectory-based detection, and the geometry of agent security.
I2TP: Information-Theoretic Identity & Threat Protocol — Patent pending
Latest paper · April 2026
Cross-Session Threats: When the Attack Lives in the Aggregate
AI agent guardrails are memoryless. An adversary spreads a single attack across dozens of sessions and slips past every session-bound detector. We frame cross-session threat detection as an information bottleneck, release a benchmark (CSTM-Bench), and show that bounded coreset memory is the only architecture whose recall survives adversarial rewriting.
Read the gist
The Missing Lens on AI Agent Identity
Agent identity is not a static concept. It's a trajectory through an information manifold — and every threat is a deviation from the intended path.
Read Article
The Future of Generative AI Security is Compressive
Exploring adaptive prompt injections and how reasoning-layer security provides superior protection against evolving AI threats.
Read Article
Multi-Stage Attack Analysis: How Thought Entities Combine into Complex Threats
Understanding how atomic attack components combine to form multi-stage threats, and how token-level analysis reveals complex attack patterns before they execute.
Read Article
Conceptual Security Monitoring: From Events to Thoughts
As agentic AI systems take actions, security shifts from 'what happened?' to 'what was the model trying to do—and why?' Thought-level entities must become first-class in security monitoring.
Read Article