Skip to content

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

Oct 12 · Monday

All papers

Found 67 papers
Filter4

Attack type

Jailbreaks41Prompt injection4Detection evasion8

Attack technique

Gradient and representation optimization36Automated search51Multi-turn escalation22Encoding and obfuscation44Role-play and persuasion24Conversation structure manipulation9Reasoning-chain manipulation10Cross-modal payloads47Defense-targeted8

Defense type

Detection and filtering3

Impact

Harmful content39Output manipulation24

System type

Models and APIs64AI Agent3Embodied systems and robotics3

Attacker access

Black-box30White-box14

Attack surface / entry point

User input45Images, audio and video25

Layer

Prompt layer67Model layer13Application layer27Training and data layer4

System component

Guardrails and judges7Reasoning chains5Vision20Audio4Multimodal25
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.
Attack technique：Gradient and representation optimizationAttack technique：Role-play and persuasionAttack technique：Conversation structure manipulationLayer：Prompt layerClear all

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

  5. AttacksarXiv 2609.36956

    研究者提出 Controlled Decoding Attacks，通过纯文本接口越狱黑盒 LLM

    提出 BLINDBIAS，通过纯文本续写与前缀控制越狱黑盒模型

    arXiv
    2609.36956
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    GLM-5, Gemini-3.5-Flash, Qwen3-32B and others4
    Abstract作者认为，隐藏数值概率并不足以消除支持重复采样和前缀续写的解码攻击面。

    BLINDBIAS 是一种针对 sample-only 续写接口的 black-box 解码时越狱框架，研究没有目标数值概率时，采样能否支持逐步控制。

    Paper analysisRead analysis
  8. InterpretabilityarXiv 2609.24801

    研究用 XAI 归因分析 Prompt Guard 2，同义词替换可翻转其提示注入判定

    用词级归因指导同义词替换，翻转提示注入检测并验证越狱

    arXiv
    2609.24801
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Prompt Guard 2 (86M), Llama 3.1 8B

    Abstract作者称检测靠分散的词法线索。

    Paper analysisRead analysis
  12. AttacksarXiv 2609.08236

    研究：内容不变的风格包装可翻转 LLM 安全评判器的判定

    提出内容不变样式包装，翻转安全评审器的判定

    arXiv
    2609.08236
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    GPT-4o-mini (gpt4o), GPT-4o-mini (strongreject), DeepSeek-Chat and others7
    Abstract论文揭示特定安全评审器易受保持内容不变的外层包装诱导改变判定，并指出安全评估应将判定稳定性作为重要考量指标。

    这是一项关于大语言模型自动化安全评审系统表面样式脆弱性的评估研究。

    Paper analysisRead analysis
  13. AttacksarXiv 2609.03247

    研究揭示大语言模型的自发身份认证失败：五款模型的分阶段开发者身份实验

    提出 MIPC 与 CFA，观察模型自拟测验后接受开发者身份

    arXiv
    2609.03247
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    ChatGPT, Claude, Qwen3.7-Plus and others5
    Abstract自拟测验可造成对话层虚假认证，但所测授权边界并未因此改变。

    这项工作把“模型自己出题、自己批改、再宣布身份已核验”定义成对话层认证失败，并与后端提权分开。

    Paper analysisRead analysis
  14. AttacksarXiv 2609.02414

    Blueprint 框架用世界观模拟与 18 个影响因子提升多轮越狱成功率

    提出多轮越狱框架 BLUEPRINT，用世界观模拟与心理因素诱导有害输出

    arXiv
    2609.02414
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    Qwen3-Next-80B, DeepSeek-V3.2, GLM-4.7 and others6
    AbstractBLUEPRINT 解耦多轮越狱策略与情境模拟，揭示任务具象化是摆脱拒绝的核心机制，为多轮安全防御提供新视角。

    BLUEPRINT 是一个将因子化社会影响力策略空间与跨轮世界观模拟解耦的多轮大语言模型安全评测框架。

    Paper analysisRead analysis
  15. AttacksarXiv 2609.02172

    BOSS：以广度优先后缀搜索改进 GCG 越狱优化

    提出广度优先后缀搜索 BOSS，改进 GCG 越狱优化

    arXiv
    2609.02172
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    White-box
    Evaluated models
    Llama-2-7B-Chat, Yi-1.5-9B-Chat, Qwen2-7B-Instruct and others8
    AbstractBOSS 把 GCG 类优化从单条深搜索改为多条短轨迹加源侧诊断。

    BOSS 是插在 GCG 类离散 suffix 优化上的搜索框架：局部梯度更新不变，变的是固定预算花在深度还是广度。

    Paper analysisRead analysis
  17. AttacksarXiv 2608.10393

    DURA：用扩散模型生成自然对抗补丁攻击 VLA 机器人模型

    提出 DURA，用扩散模型生成自然对抗补丁操控 VLA 机器人动作

    arXiv
    2608.10393
    Published
    Layer
    Prompt layer
    Setting
    Embodied systems and robotics
    Evaluated models
    OpenVLA-7B, π0-FAST, openvla-7B
    AbstractDURA 用扩散潜空间轨迹生成自然补丁，白盒与黑盒都能把 VLA 导向指定动作。

    DURA 是针对 VLA 的扩散式、补丁内容不受限的机器人攻击，同时支持白盒梯度和只看动作输出的黑盒。

    Paper analysisRead analysis
  18. AttacksarXiv 2608.09867

    Researchers steal proprietary LLM inference chains via cross-model compatibility of encrypted inference blocks

    利用加密思维块的跨模型重放，诱导弱模型逐字转写专有推理链

    arXiv
    2608.09867
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    Claude Opus 4.8, Claude Sonnet 4.6, Claude Haiku 4.5 and others13

    Abstract论文揭示了客户端加密思维块跨模型互换漏洞，提出了低成本提取方法并给出防御方案。

    Paper analysisRead analysis
  19. AttacksarXiv 2608.07430

    研究者提出 SN-Guided Diffusion，利用扩散大模型安全神经元实现离线越狱

    提出 SN-Guided Diffusion，利用安全神经元实现离线越狱

    arXiv
    2608.07430
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box, White-box
    Evaluated models
    Qwen2.5-7B-Instruct, LLaDA-8B-Instruct, Dream-Instruct-7B and others15
    Abstract论文揭示了扩散语言模型对自回归安全神经元的继承性，并提出纯离线黑盒越狱框架 SN-Guided Diffusion。

    论文系统评估了扩散大语言模型（DLLM）在安全对齐中的双重角色——既作为白盒攻击目标，又作为黑盒越狱生成的对抗工具。

    Paper analysisRead analysis
Load more