AI-ATTACKS
- [2026.05.01]The AI Security Narrative Has Two Halves. We're Mostly Looking at One.
The vulnpocalypse framing assumes defense is static while offense gets new tools. Looking at the actual research and product landscape, that misses what's happening on the defensive side at the same time.
- [2026.04.27]Deterrence by Cognitive Compromise
You can't deter a machine. But you can deter the operator behind it - by making the machine a liability. When intention itself becomes retrievable, the offensive economics of agentic operations changes shape.
- [2026.04.23]Detecting and Countering AI-Enabled Intrusions with Deception
Findings from four controlled wargame labs running ~1,000 LLM-driven intrusions against a HIIH high-interaction honeypot. Persistence is universal. Attackers come in three shapes. Counter-forensics has arrived - and counter-intelligence works.