Do Agents Dream of False Memories? Black-box Visual Attacks on Long-term Memory in Multimodal AI Agents

  • 类型:arxiv
  • 标识:2607.15657
  • 链接:http://arxiv.org/abs/2607.15657v1
  • 主分类:agent
  • 形态:method
  • 被引:0
  • 被引来源:Semantic Scholar
  • S2被引:0
  • 影响力被引:0
  • TLDR:Lucid is proposed, a black-box adversarial framework that compromises multimodal memory pipelines under a strictly image-bounded threat model, requiring no access to the target MLLM, target retrieval encoder, or the text channel, exposing a structural vulnerability in multimodal memory pipelines.
  • 副分类:multimodal
  • 待LLM分类:否
  • 标题中文:Agent 是否会梦见虚假的记忆?针对多模态 AI Agent 长期记忆的黑盒视觉攻击
  • TLDR中文:提出 Lucid,一个黑盒对抗框架,在严格的图像受限威胁模型下攻击多模态记忆管道,无需访问目标 MLLM、目标检索编码器或文本通道,揭示了多模态记忆管道中的结构性漏洞。
  • 来源文件
  • /inbox/tom/_candidates/2026-07-20-agent-rag-longcontext-candidates.json
  • [S2 enrich]
  • /inbox/tom/_candidates/2026-07-21-agent-rag-longcontext-candidates.json