Microsoft warns attackers can secretly manipulate AI recommendations

Microsoft warns attackers can secretly manipulate AI recommendations

Microsoft has warned of a new tactic called AI Recommendation Poisoning, where hidden instructions inside links can manipulate an assistant’s memory and bias future recommendations. The company advises users to review and clear saved AI memories to reduce risk.

Comments

No comments yet. Why don’t you start the discussion?

Leave a Reply

Your email address will not be published. Required fields are marked *