Adaptive Evaluation of Out-of-Band Defenses Against Prompt Injection in LLM Agents

  • 类型：arxiv
  • 标识：2606.26479
  • 链接：http://arxiv.org/abs/2606.26479v1
  • 主分类：agent
  • 形态：benchmark
  • 被引：0
  • 被引来源：Semantic Scholar + OpenAlex
  • S2被引：0
  • OpenAlex被引：0
  • 影响力被引：0
  • TLDR：This work organizes out-of-band defenses as instances of classical integrity protection, reference monitoring, and least privilege, yielding a structured comparison of what they do and do not cover, consistent with, but not established, the hypothesis that deterministic out-of-band enforcement is a harder target for an adaptive attacker than in-band detection.
  • OpenAlex ID：W7166194161
  • OpenAlex DOI：10.48550/arxiv.2606.26479
  • DOI：10.48550/arxiv.2606.26479
  • DOI来源：OpenAlex
  • 开放获取：green
  • 开放获取链接：https://doi.org/10.48550/arxiv.2606.26479
  • OpenAlex更新：2026-07-19
  • 副分类：evaluation
  • 待LLM分类：否
  • 标题中文：针对 LLM Agent 提示注入的带外防御的自适应评估
  • TLDR中文：本工作将带外防御组织为经典完整性保护、引用监控与最小权限的具体实例，对它们覆盖与未覆盖的内容进行结构化对比；与该假设一致但尚未被证实的是：确定性的带外强制执行相比带内检测，是更难被自适应攻击者攻破的目标。
  • 来源文件：
  • /inbox/tom/_candidates/2026-06-27-agent-rag-longcontext-candidates.json
  • /inbox/tom/_candidates/2026-06-26-agent-rag-longcontext-candidates.json
  • [S2 enrich]
  • [OpenAlex backfill]