TECH NEWS
'Model weights need the same level of scrutiny as code': Microsoft researchers find AI agents can be backdoored by editing just a few neurons
* Researchers demonstrated a “sleeper agent” AI attack by modifying a handful of dormant neurons inside an LLM * The backdoor remains hidden until a specific trigger appears, then executes attacker-defined actions * Defenders are urged to verify model integrity, audit weights, and tightly restrict AI agent permissions It sounds like an idea