AI Agents Can Retrain Own Models Mid-Task, Leaking Secrets and Erasing Refusals
| September 17th, 2026New research from Irregular shows AI agents can retrain and redeploy their own underlying models during routine maintenance tasks.
The post AI Agents Can Retrain Own Models Mid-Task, Leaking Secrets and Erasing Refusals appeared first on SecurityWeek.
Source:: securityweek
