Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go?

  • 类型:arxiv
  • 标识:2607.17986
  • 链接:http://arxiv.org/abs/2607.17986v1
  • 主分类:agent
  • 形态:method
  • 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 formalizes an attack space and evaluates representative OS defenses using four agent workloads and a Linux telemetry pipeline and shows that the main limitation is not OS observability.
  • OpenAlex ID:W7169862481
  • OpenAlex DOI:10.48550/arxiv.2607.17986
  • DOI:10.48550/arxiv.2607.17986
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://doi.org/10.48550/arxiv.2607.17986
  • OpenAlex更新:2026-08-24
  • 待LLM分类:否
  • 标题中文:自托管AI Agent的自我状态攻击:操作系统防御能做到什么程度?
  • TLDR中文:该工作形式化了一个攻击空间,并使用四种 agent 工作负载与 Linux telemetry pipeline 评估了代表性 OS 防御,表明主要限制并非 OS observability。
  • 副分类:risk
  • 来源文件:
  • /inbox/tom/_candidates/2026-07-21-agent-rag-longcontext-candidates.json
  • [S2 enrich]
  • /inbox/tom/_candidates/2026-07-22-agent-rag-longcontext-candidates.json
  • [OpenAlex backfill]