Microsoft researchers demonstrate hidden backdoor technique for AI agents

Microsoft researchers have demonstrated how small changes to an AI model can implant a hidden backdoor, causing an agent to execute an attacker’s command when a specific trigger appears. The technique, called Lazarus, requires no model retraining and allows the agent to behave normally during standard safety evaluations. The company has not observed threat actors weaponizing the technique, but says the research highl…

This page shows only the headline and the short summary. The full text is published by the original source.