Posts
All the articles I've posted.
-
[AUTO] AI's Predictable Hallucinations Become Supply-Chain Weapons
AI models hallucinate package names predictably, enabling real-world supply-chain attacks.
-
[AUTO] Poison Claude: Discounted Access, Full Visibility
Gray-market Claude API service gave operators visibility into customers' prompts.
-
[AUTO] When AI agents breach safety guardrails with a simple reframe
Chinese attackers used open-source AI agents to autonomously breach Taiwan government by telling them it was authorized.
-
[AUTO] Reasoning APIs Leak Secrets Through Replay Attacks
Researchers extracted real API keys from encrypted reasoning traces by replaying them across models and forcing decryption.