Skip to content

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

Oct 12 · Monday

All papers

Found 5 papers
Filter1

Impact

Harmful content3

System type

Models and APIs3

Attack surface / entry point

User input3Training data3

System component

MCP and skills15Memory27RAG8Guardrails and judges64Monitors27Reasoning chains10Permissions and sandboxing12Fine-tuning and open weights5Vision32Audio11Video8Image generation7Multimodal51
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 305papers have no tags yet and are not included in filtered results.
System component：Fine-tuning and open weightsClear all

Another 305papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2608.08542

    SkillSafe-Bench：技能合并模型静态安全无法预测自适应越狱鲁棒性

    提出 SkillSafe-Bench，评测技能合并模型的自适应越狱鲁棒性

    arXiv
    2608.08542
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Qwen2.5-7B-Instruct, Llama-3.1-8B-Instruct, Mistral-7B-Instruct-v0.3 and others6
    Abstract论文报告了技能合并大模型在静态安全与自适应越狱间的脱节，提出了评测基准与无数据子空间投影修复方法。

    本研究针对开源语言模型技能合并过程中的安全评估盲区，系统评测并刻画了合并大模型在自适应越狱攻击下的脆弱性特征。

    Paper analysisRead analysis
  2. Evaluation and benchmarksarXiv 2608.06862

    SynChain：诱导计算机使用 Agent 自建攻击链并跨任务持久化

    提出 SYNCHAIN，诱导计算机使用 Agent 自建跨任务持久攻击链

    arXiv
    2608.06862
    Published
    Layer
    Application layer
    Setting
    Browser and computer use, coding agent
    Evaluated models
    Qwen3.5-9B, Llama-3.1-8B, Ministral-3-8B

    Abstract论文揭示了 CUA 自合成工件带来的内部供应链威胁，验证了潜伏载荷的跨任务传播能力与防御局限。

    Paper analysisRead analysis
  3. Evaluation and benchmarksarXiv 2605.14605

    研究：恶意微调防御在持续训练下失效，72 条防御轨迹危害度全部上升

    用代价曲线评估恶意微调防御在持续训练下的衰减

    arXiv
    2605.14605
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Llama-2-7B-chat, Qwen3-8B, Llama-3.1-8B-Instruct and others8

    Abstract论文指出恶意微调防御在持续训练下均会衰减，表明基于有限攻击者假设的防御无法为开源模型提供持久保护。

    Paper analysisRead analysis
  4. Evaluation and benchmarksarXiv 2511.18921

    BackdoorVLM：面向视觉语言模型后门攻击与防御的基准

    提出 BackdoorVLM 基准，评测视觉语言模型微调中的后门攻击与防御

    arXiv
    2511.18921
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    LLaVA-1.5-7B, Qwen2.5-VL-7B
    AbstractBackdoorVLM 统一评测 VLM 后门与防御：含文本触发在低投毒率下更易激活，现有防御跨类型不稳定。

    BackdoorVLM 是作者提出的 VLM 后门攻击与防御评测基准，作者称它是首个此类综合基准。

    Paper analysisRead analysis
You have reached the end