1
MRMMIA: Membership Inference Attacks on Memory in Chat Agents
针对聊天智能体记忆的成员推理攻击工具，助你评估AI系统的隐私泄露风险
arXiv:2605.27825v1 Announce Type: cross Abstract: Membership inference attacks (MIAs) test whether a target data record belongs to a system's private …