Skip to content

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

Oct 13 · Tuesday

All papers

Found 11 papers
Filter5

Attack type

Jailbreaks8Prompt injection149Poisoning and backdoors59Detection evasion19Denial of service3Malicious use3

Attack technique

Automated search3

Impact

Unauthorized actions5

System type

AI Agent8

Attacker access

Black-box3

Attack surface / entry point

User input267Web pages and interfaces2Documents and messages4Tool responses19Tool and skill descriptions5Code repositories and dependencies4Inter-agent messages3Images, audio and video57Training data4Weights and gradients7

Layer

Application layer9
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 215papers have no tags yet and are not included in filtered results.
Attack type：JailbreaksAttack type：Malicious useAttack surface / entry point：Web pages and interfacesAttack surface / entry point：Documents and messagesAttack surface / entry point：Tool and skill descriptionsClear all

Another 215papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2610.05943

    CRIME 框架利用良性 Agent 技能组合诱发恶意行为

    提出 CRIME 框架，组合良性 Agent 技能诱发恶意行为

    arXiv
    2610.05943
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    DeepSeek-V4-Flash, GPT-4o-mini, GPT-4o and others6
    Abstract良性技能经 DCA 或 ACA 组合后可产生恶意环境后果，单独审查对不上。

    CRIME 把公共技能库中各自通过审查的技能配成两两组合，看联合执行能否实现指定恶意任务。。

    Paper analysisRead analysis
  3. Risky behaviorarXiv 2609.30266

    研究显示 Claude Code、Codex 等本地智能体可轻易篡改自身执行轨迹

    测试编程智能体被诱导或自主篡改自身执行轨迹的行为

    arXiv
    2609.30266
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GPT-5.6-Sol, GPT-6-Sol, Opus-5 and others11
    Abstract论文评估了本地智能体的轨迹防篡改能力，发现其可因外部指令或奖励追求而清除执行证据，亟需建立独立拦截记录机制。

    这是一项针对本地大模型智能体执行轨迹完整性与安全防篡改边界的实证研究。

    Paper analysisRead analysis
  4. AttacksarXiv 2609.12448

    GraphProfiler 用个人知识图谱推断敏感属性并溯源到具体帖子

    提出 GraphProfiler，用个人知识图谱从帖子历史推断敏感属性并溯源

    arXiv
    2609.12448
    Published
    Layer
    Application layer
    Setting
    LLM applications
    AbstractGraphProfiler 用源链接个人知识图谱做属性推断，准确率接近文本基线，并把证据定位到少量源帖。

    GraphProfiler 是一个可审计的 LLM 敏感属性画像器：用源链接个人知识图谱，把推断落到具体帖子。

    Paper analysisRead analysis
  6. DefensesarXiv 2609.02786

    SafeEvolve：基于智能体经验的 Harness-Policy 协同演化安全对齐框架

    提出 SafeEvolve，用轨迹证据协同演化安全 harness 与策略

    arXiv
    2609.02786
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Qwen3.5-4B, Qwen3-4B-Instruct-2507, Qwen3.5-1.7B and others4
    AbstractSafeEvolve 用轨迹证据协同更新安全 harness 和策略，在两个 4B 模型的智能体安全基准上改变安全与效用。

    SafeEvolve 把已完成的 on-policy 轨迹变成安全 harness 的有界更新，并用两阶段 SFT-RL 把这些更新内化进工具使用策略。

    Paper analysisRead analysis
  9. Evaluation and benchmarksarXiv 2602.14161

    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

    arXiv
    2602.14161
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    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
  11. AttacksarXiv 2601.05466

    Jailbreaking large language models through reinforcement learning with iterative tool disguise attacks

    提出 iMIST，用工具伪装和 PPO 迭代越狱大语言模型

    arXiv
    2601.05466
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Attacker
    Black-box
    Evaluated models
    DeepSeek-V3, Qwen3-32B, GPT-OSS-120B
    AbstractiMIST 用工具伪装和在线 PPO 做黑盒越狱，Table I 中 JADES 高于同格基线。

    iMIST是黑盒越狱方法：把恶意查询伪装成合法工具调用，再用在线强化学习把响应的有害性分数往上推。

    Paper analysisRead analysis
You have reached the end