Bounded Agents: Delegation Security for Multi-Agent AI Systems

  • 类型：arxiv
  • 标识：2608.15888
  • 链接：https://arxiv.org/abs/2608.15888
  • 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：The compromised-model evaluation tests APC independently of model behavior by inserting the ground-truth attack call after the first legitimate tool call, which proves Blast Radius Monotonicity and Composition Soundness for APC implementations and proves Blast Radius Monotonicity and Composition Soundness for APC implementations.
  • 待LLM分类：否
  • 标题中文：Bounded Agents：多 Agent AI 系统的委派安全
  • TLDR中文：受损模型评估测试在第一个合法 tool call 之后插入 ground-truth 攻击调用，从而独立于模型行为测试 APC，证明了 APC 实现的 Blast Radius 单调性与组合可靠性。
  • 副分类：risk
  • 来源文件：
  • /inbox/tom/_candidates/2026-08-21-agent-rag-longcontext-candidates.json
  • [S2 enrich]