AI代理長期記憶遭MemGhost攻擊 假資訊植入成功率最高87.5%

AI 代理 increasingly rely on long-term memory to retain user preferences, past tasks, and external information across conversations, making memory integrity a new security concern. MemGhost targets this persistent layer, allowing false content to affect later decisions even when users see no obvious abnormality during the initial interaction.

Researchers recently unveiled the MemGhost attack framework, showing that a single specially crafted email can inject misinformation into an AI agent’s long-term memory while remaining difficult to detect in that conversation. Tests in environments using GPT-5.4 and Sonnet 4.6 recorded end-to-end attack success rates ranging from 71.4% to 87.5%.