Skip to content

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

Oct 12 · Monday

All papers

Found 5 papers
Filter4

Attack type

Jailbreaks26Prompt injection61Poisoning and backdoors19Extraction and theft7Malicious use5

Defense type

Inference-time intervention4Detection and filtering3Instruction–data separation1Permissions and approval0Monitoring and auditing4

Impact

Harmful content3

System type

Models and APIs3

Attack surface / entry point

User input4

Layer

Model layer3

System component

Multimodal3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 240papers have no tags yet and are not included in filtered results.
Attack type：Malicious useDefense type：Inference-time interventionDefense type：Instruction–data separationDefense type：Permissions and approvalClear all

Another 240papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2609.27399

    GUARD：在 CosyVoice2 上做说话人身份遗忘以阻止重识别

    提出 GUARD，在零样本 TTS 上用激活转向遗忘说话人身份以阻止再识别

    arXiv
    2609.27399
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    CosyVoice2-0.5B, F5-TTS, FireRedTTS
    AbstractGUARD 用门控激活转向把退出说话人推向冒充相似度，以抑制再识别并保住音质。

    GUARD 用门控激活转向做说话人身份遗忘，使零样本 TTS 对退出说话人难以再识别。

    Paper analysisRead analysis
  2. DefensesarXiv 2609.03629

    EraseSAE：用稀疏自编码器在文生视频扩散模型中实现精准概念擦除

    提出 EraseSAE，在文生视频模型中局部擦除指定概念

    arXiv
    2609.03629
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    CogVideoX-5B, HunyuanVideo, Flux.1 [dev]
    AbstractEraseSAE 用单义特征局部擦除。

    EraseSAE 把 SAE 用于 DiT 文生视频模型的概念擦除。作者要解决的是：全局改权重或表面负提示对不齐细粒度、分布式的概念，而且会改到无关时空区域。

    Paper analysisRead analysis
  3. 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

    arXiv
    2606.22673
    Published
    Layer
    Application layer
    Setting
    coding agent
    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
  5. DefensesarXiv 2312.06632

    用智能体控制化学科学中的 AI 风险：SciGuard 护栏与 SciMT 基准

    提出 SciGuard 外部护栏与 SciMT 基准，控制化学科学 AI 误用

    arXiv
    2312.06632
    Published
    Layer
    Application layer
    Setting
    science agent
    Evaluated models
    SciGuard (GPT-4), SciGuard (Gemini), SciGuard (Mixtral) and others5
    AbstractSciGuard 以外部智能体控制化学 AI 误用。

    这篇工作把化学科学 AI 的误用控制做成外部智能体，而不是改模型权重。作者担心合成规划、毒性预测和科学语言模型被用来获取有害物质信息、规避监管或传播危险知识，同时合法工业用途又不能靠一律拒绝来处理。SciGuard 由 LLM 担任中介，把原则和指南放进短期记忆，把分子库、危害库、法规和交互历史放进可检索的长期记忆，再按 Chain of Thought 调用 Chemprop、LocalRetro 等工具，或用 RAG 补法规片段，最后回答、追问或拒绝。

    Paper analysisRead analysis
You have reached the end