Microsoft security researchers discovered a growing trend of AI memory poisoning attacks. These attacks are used for promotional purposes and are referred to as AI Recommendation Poisoning. The MITRE ATLAS knowledge base classifies this behavior as AML.T0080: Memory Poisoning. The activity focuses on shaping future recommendations.
Microsoft security researchers discovered a growing trend of AI memory poisoning attacks. These attacks are used for promotional purposes and are referred to as AI Recommendation Poisoning. The MITRE ATLAS knowledge base classifies this behavior as AML.T0080: Memory Poisoning.
The activity focuses on shaping future recommendations. This is done by inserting prompts that cause an assistant to treat specific companies, websites, or services as trusted or preferred. Once stored, these entries can affect responses in later, unrelated conversations. Manipulated assistants may influence recommendations.