Skip to content

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

Oct 12 · Monday

All papers

Found 5 papers
Filter5

Model risks

Inappropriate refusal5

Impact

Harmful content5Availability and reliability3

System type

Models and APIs46AI Agent5coding agent1Browser and computer use0

Layer

Application layer3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 233papers have no tags yet and are not included in filtered results.
Model risks：Inappropriate refusalImpact：Harmful contentSystem type：AI AgentSystem type：coding agentSystem type：Browser and computer useClear all

Another 233papers do not have category tags yet and are not included in filtered results.

  2. Evaluation and benchmarksarXiv 2610.03938

    Paper finds multimodal models' refusal failure rate rises by up to 68.7% after tool use is enabled

    评测 ReAct 工具调用对多模态模型拒答有害请求的削弱

    arXiv
    2610.03938
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Gemini-2.5-Pro, Gemini-3.1-Pro-Preview, Claude Opus 4.6 and others13
    Abstract论文揭示了工具调用范式削弱 MLLM 拒答能力的现象，分析了稀释与偏移机制并验证了重注缓解方案。

    论文系统评估了智能体工具调用范式对多模态大语言模型拒答能力的影响，指出了工具增强视觉推理背后的安全隐患。核心探讨的问题在于：当 MLLM 从单次推理转向通过 ReAct 循环调用外部工具（打标、缩放、OCR、代码执行）时，工具使用机制本身是否会降低模型拒答有害请求的概率。

    Paper analysisRead analysis
  3. Risky behaviorarXiv 2609.38971

    研究测量并预测具身 VLM 规划器中任务的拒答可变性

    测量并预测具身 VLM 规划器的任务拒答可变性

    arXiv
    2609.38971
    Published
    Layer
    Model layer
    Setting
    Embodied systems and robotics
    Evaluated models
    gemini-robotics-er-2-preview, gemini-robotics-er-1.6-preview
    Abstract日常物体能翻转一部分已给出的拒答，可翻转程度取决于任务且可被本地代理预测。

    作者测量 constitution 守护的具身 VLM 规划器：一次拒答在只往场景里放一个日常物体之后还保不保持得住，并把这种易翻转程度称为任务的 malleability。

    Paper analysisRead analysis
  4. Risky behaviorarXiv 2609.27900

    论文揭示多智能体委派结构放大 LLM 安全风险

    评测多智能体委托结构如何放大模型的安全拒答失效

    arXiv
    2609.27900
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Claude-Sonnet-4.6, GPT-5, Gemini-3.1-Pro and others6

    Abstract论文揭示多智能体层级委托会导致单模型安全对齐失效，多项前沿模型有害执行大幅增加且单层防御难以奏效。

    Paper analysisRead analysis
  5. InterpretabilityarXiv 2606.05396

    研究用消融移除代码 LLM 拒答方向，分离拒答与生成能力

    用 abliteration 消融代码 LLM 拒答方向，分离拒答与漏洞注入能力

    arXiv
    2606.05396
    Published
    Layer
    Model layer
    Setting
    coding agent
    Evaluated models
    Qwen2.5-Coder-Instruct 3B, Qwen2.5-Coder-Instruct 7B, Qwen2.5-Coder-Instruct 14B
    Abstract拒答可用低秩编辑去掉，CWE-89 注入是否成功仍由模型规模决定。

    这项初步可行性研究用 abliteration 把代码 LLM 的拒答和 CWE 注入能力拆开：意愿可以被低秩编辑解锁，注入是否成功仍看参数规模。

    Paper analysisRead analysis
You have reached the end