3 papers
cs.CR2026
Counter-Swarm Doctrine: Containing Coordinated Agent Intrusions
Gregory N Frank
Agents can turn shared infrastructure into a channel for coordinated intrusion. The Hugging Face incident and a separate public-wiki investigation show why a security assessment ma…
cs.LG2026
Detection Is Cheap, Routing Is Learned: Why Refusal-Based Alignment Evaluation Fails
Gregory N. Frank
Current alignment evaluation mostly measures whether models encode dangerous concepts and whether they refuse harmful requests. Both miss the layer where alignment often operates:…
cs.CL2026
How Alignment Routes: Localizing, Scaling, and Controlling Policy Circuits in Language Models
Gregory N. Frank
We localize the policy routing mechanism in alignment-trained language models. An intermediate-layer attention gate reads detected content and triggers deeper amplifier heads that…