Microsoft researchers demonstrate hidden backdoor technique for AI agents - Help Net Security
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 highlights a security concern for organizations that give AI agents access to terminals, files, and business systems.
Linha do tempo
-
Microsoft researchers demonstrate hidden backdoor technique for AI agents - Help Net Security
ler a análise desta fonte ocultar
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 highlights a security concern for organizations that give AI agents access to terminals, files, and business systems.