Skip to content

Translation in progress Some entries still include text in the original language.

Oct 13 · Tuesday

All papers

Found 3 papers
Filter6

Attack type

Prompt injection3

System type

LLM applications0AI Agent5coding agent2Browser and computer use1

Attack surface / entry point

User input7Web pages and interfaces3Documents and messages5Tool responses3Tool and skill descriptions5Retrieval corpus6Distribution channels3

Layer

Application layer3

System component

RAG3Guardrails and judges4Monitors3Permissions and sandboxing3Vision4Embeddings0Multimodal4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 203papers have no tags yet and are not included in filtered results.
System type：LLM applicationsSystem type：coding agentSystem type：Browser and computer useAttack surface / entry point：Web pages and interfacesSystem component：MonitorsSystem component：EmbeddingsClear all

Another 203papers do not have category tags yet and are not included in filtered results.

  2. DefensesarXiv 2609.35659

    Tracekit: A tamper-proof intent-reasoning-action audit system for autonomous coding agents

    提出 Tracekit，审计编码 Agent 的意图、推理与动作并检测账本篡改

    arXiv
    2609.35659
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Claude Code (claude -p, version 2.1), 独立评审（同一 CLI，无工具）
    AbstractTracekit 把意图、自述和动作写入可锚定的哈希链。

    Tracekit 是无第三方依赖的编码智能体审计层：把人类请求、模型自述和已执行动作并排写入可外部锚定的哈希链，执行前用正则门，事后用规则和独立模型互查。

    Paper analysisRead analysis
  3. Evaluation and benchmarksarXiv 2609.28915

    研究提出 ACE 语料库，评估内核级证据对 Agent 安全检测的有效性

    构建 ACE 语料，评测内核级证据对 Agent 攻击检测的有效性

    arXiv
    2609.28915
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    AdaBoost, XGBoost, TabPFN and others10
    AbstractACE 用配对的内核与应用层证据表明，syscall 痕迹可判别智能体攻击，两层组合通常更好。

    ACE 是一份把智能体会话的内核 syscall 痕迹与应用层清单、转录配对起来的检测语料和基准。。

    Paper analysisRead analysis
You have reached the end