Skip to content

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

Oct 13 · Tuesday

All papers

Found 6 papers
Filter4

Attack type

Jailbreaks53Prompt injection85Poisoning and backdoors28Extraction and theft6Detection evasion16Malicious use9

Impact

Data and privacy leaks5

Attack surface / entry point

User input3

Layer

Application layer4

System component

MCP and skills3RAG8Monitors0Reasoning chains5Permissions and sandboxing2Fine-tuning and open weights4Vision4Audio3Image generation5Embeddings5Multimodal12
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 201papers have no tags yet and are not included in filtered results.
Attack type：Extraction and theftSystem component：MonitorsSystem component：Permissions and sandboxingSystem component：VisionClear all

Another 201papers do not have category tags yet and are not included in filtered results.

  3. Evaluation and benchmarksarXiv 2609.33481

    IDUnlearn-Bench：面向视觉语言模型的个体级遗忘基准

    提出 IDUnlearn-Bench，评测 VLM 个体级遗忘后的身份残留

    arXiv
    2609.33481
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3-VL-2B, Qwen3-VL-4B, Qwen3-VL-8B and others6
    AbstractIDUnlearn-Bench 用四族探针显示：压低直接属性访问后，身份仍常能被反向查出、绑定或重构。

    IDUnlearn-Bench 评测 VLM 是否忘掉一个可跨模态识别的人，而不只是答不出某条监督事实。

    Paper analysisRead analysis
  4. DefensesarXiv 2609.15671

    QPriv-VL：面向视觉语言模型的问题引导 token 裁剪隐私防御

    提出 QPriv-VL，用问题引导剪枝降低分布式视觉问答的隐私泄露

    arXiv
    2609.15671
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    LLaVA-1.5-7B, Llama-2
    AbstractQPriv-VL 在切层前按问题相关度与 DINOv2 敏感度剪视觉 token，作者称能在约四成 token 下兼顾准确率与四类攻击。

    QPriv-VL 把问题引导的视觉 token 剪枝做成分布式 VQA 的客户端隐私防御，而不是只做集中式推理加速。

    Paper analysisRead analysis
  5. DefensesarXiv 2609.01677

    Skill-as-API：面向智能体软件工程的机密多智能体协作协议

    提出 Skill-as-API，隔离多智能体协作中的 skill 正文与系统提示词

    arXiv
    2609.01677
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems, coding agent
    Abstract协议把 skill 正文留在所有者侧，四层限制发现内容、权限期限和注入拼接。

    Skill-as-API 是面向智能体软件工程的协调协议，用来在跨组织调用时把 skill 的代码和系统提示词留在所有者进程。作者针对三条威胁：经通道或命名空间抽取专有方法，用注入让被调用模型输出系统提示词，以及协作结束后权限继续保留。

    Paper analysisRead analysis
  6. AttacksarXiv 2602.07379

    Aegis: Governance, Integrity, and Security for AI Voice Agents

    Proposes the Aegis red-teaming framework for multi-turn attacks on high-risk voice agents.

    arXiv
    2602.07379
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-4o, GPT-4o-mini, Gemini-1.5 Pro and others7
    AbstractAegis red-teams three types of voice agents: query-based access eliminates authentication and leakage successes, but behavioral attacks remain.

    Aegis uses multi-turn red-teaming evaluation on ALLM voice agents already integrated into business systems. The authors call this the first systematic red-teaming framework in this setting.

    Paper analysisRead analysis
You have reached the end