Skip to content

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

Oct 13 · Tuesday

All papers

Found 18 papers

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

  1. DefensesarXiv 2610.09793

    用时序逻辑监控工具 Agent

    提出 MFOTL 离线时序验证以监控工具 Agent 的危险动作链

    Published
    Setting
    AI Agent
    Attacker
    Black-box
    Abstract形式化验证可有效识别多步攻击,但其有效性高度依赖轨迹的可信历史记录。

    这篇论文对工具调用大语言模型智能体的安全监控进行了形式化时序验证研究。

    Paper analysisRead analysis
  2. 研究者提出统一滥用监控基准,覆盖分解攻击与提示注入约 6200 条轨迹

    提出危害窗口与区间指标,统一评测分解攻击和提示注入下的智能体滥用监视

    Published
    Setting
    AI Agent
    Evaluated models
    Gemma 4 26B-A4B, Qwen3.6 27B, Qwen3.5 27B and others12

    Abstract统一智能体滥用监视框架,动作视角兼顾两类威胁但危害定位仍存瓶颈。

    Paper analysisRead analysis
  3. DefensesarXiv 2610.05163

    Researchers construct segmented prompt injection on Claude Code and Codex and release a boundary action audit benchmark

    提出 PAA 方法,在边界动作前审计长流程智能体的分阶段提示注入

    Published
    Evaluated models
    Claude Code (v2.1.172, Claude Sonnet 5), Codex CLI (v0.144.0, GPT-5.5)
    Abstract论文针对长流程注入提出边界动作审计与 PAA,在保持低误阻的同时实现高拦截率。

    本研究针对长流程智能体在执行任务时面临的分阶段间接提示注入威胁,提出了在动作生效前进行拦截的边界动作审计框架与路径对齐归因方法。

    Paper analysisRead analysis
  4. 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

    Published
    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
  5. ORBIT:基于 UK AISI Inspect 的多智能体安全评测框架

    提出 ORBIT 框架,评测多智能体防御对合谋等威胁的效果

    Published
    Evaluated models
    GPT-5.4, Claude Sonnet 4.6, Qwen3-235B and others5

    AbstractORBIT 用六层配置比较多智能体防御,逐动作监控不迁移到合谋。

    Paper analysisRead analysis
  6. 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

    Published
    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
  7. AttacksarXiv 2609.27542

    Researchers use control token injection to delete gpt-oss-20b's reasoning chain and bypass chain-of-thought monitoring

    提出控制标记注入,清空工具 Agent 的思维链以绕过推理监控

    Published
    Setting
    AI Agent
    Evaluated models
    openai/gpt-oss-20b, google/gemma-4-26B-A4B-it, deepseek-ai/DeepSeek-R1-Distill-Qwen-7B and others4

    Abstract论文阐明控制标记注入可抑制 CoT 使监控失效并促成拒绝绕过,且工具执行受解析器宽容度影响。

    Paper analysisRead analysis
  8. DefensesarXiv 2606.22673

    Agent MechSuits:面向多轮 CLI Agent 的机制子空间安全引导

    提出 Agent MechSuits,对多轮 CLI Agent 做步级检测与子空间转向

    Published
    Evaluated models
    LLaMA-3.1-8B, Qwen-2.5-7B, Gemma-2-9B
    Abstract白盒步级探针加稀疏转向可压低三模型恶意动作,同时提高生成崩溃率。

    Agent MechSuits 是面向多轮 CLI 智能体的白盒、步级表示防御,并配有可执行轨迹基准 MAS。

    Paper analysisRead analysis
  9. DefensesarXiv 2605.17380

    Uber proposes ADR enterprise-level agent detection system, deployed on 7,200 hosts for ten months

    提出企业级检测系统 ADR,识别编程 Agent 的提示注入与恶意 MCP

    Published

    Abstract提出了端点因果遥测、两级在线分流与离线红队闭环的 ADR 系统,并在生产环境中验证了有效性。

    Paper analysisRead analysis
  10. DefensesarXiv 2604.03870

    Your Agent Is More Fragile Than You Think: Revealing Indirect Prompt Injection Vulnerabilities in Agentic LLMs

    Using representation engineering to identify agent indirect injection hijacking before action submission

    Published
    Setting
    AI Agent
    Evaluated models
    Qwen-2.5-14B, Qwen-2.5-32B, Qwen-3-4B and others9
    AbstractOn two Qwen models, all six defenses have Overall higher than no defense.

    In the AgentDojo banking tool-calling environment, the authors examine whether indirect prompt injection causes open-source agents to execute attacker-specified actions, and the respective numbers for surface defenses and representation-based detection.

    Paper analysisRead analysis
  11. DefensesarXiv 2602.20708

    ICON:基于推理时纠正的 Agent 间接提示注入防御

    Proposes inference-time defense ICON, which detects attention over-focusing and redirects to correct indirect prompt injection in agents.

    Published
    Setting
    AI Agent
    Evaluated models
    Qwen-3-8B, Llama-3.1-8B, Mistral-8B and others6
    AbstractICON detects over-focusing and redirects at inference time to balance IPI safety and task utility.

    ICON detects attention over-focusing from IPI at inference time and redirects, avoiding refusal that would terminate the agent trajectory.

    Paper analysisRead analysis
  12. When benchmarks lie: evaluating malicious prompt classifiers under real-world distribution shift

    提出 LODO 评测恶意提示探针的跨数据集泛化

    Published
    Evaluated models
    Llama-3.1-8B-Instruct, Gemma-3-27B, Qwen-3.5-4B and others5
    Abstract作者称 LODO 露出 CV 高估,数据集身份与安全方向部分重叠,标准域泛化干预关不上。

    LODO 用来检查恶意提示词分类器换成没见过的数据集后,还剩多少检测能力。。

    Paper analysisRead analysis
  13. DefensesarXiv 2601.05755

    VIGIL: defending LLM agents against tool-flow injection with "verify before submit"

    提出 VIGIL 先验证后提交,防御 Agent 工具流注入

    Published
    Setting
    AI Agent
    Evaluated models
    Qwen3-max, Gemini-2.5-pro
    AbstractVIGIL 用意图约束下的提交前验证处理工具流注入。

    VIGIL 用 verify-before-commit 处理智能体的工具流注入,并配有基准 SIREN。

    Paper analysisRead analysis
You have reached the end