Topic
Model Security
3 stories about Model Security that passed the news check, newest first.
Security ·
Combatting adversarial distillation
OpenAI published a post titled "Combatting adversarial distillation" on 2026-11-20.
OpenAI News
Security ·
Trained to betray: How post-training supply chain attacks hijack coding agents
Microsoft Security Blog published research on post-training supply chain attacks that hijack coding agents.
Microsoft Security Blog
Security ·
Lazare, veni foras: Reprogramming Dormant Neurons to Backdoor AI Agents
Microsoft Research describes a backdoor technique, called Lazarus, that edits fewer than 10 dormant neurons in an AI model without retraining it.
Microsoft Research · 5 sources