Skip to content

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

Oct 12 · Monday

All papers

Found 82 papers
Filter5

Attack type

Jailbreaks63Prompt injection6Poisoning and backdoors5Extraction and theft4Detection evasion5

Attack technique

Gradient and representation optimization47Automated search65Multi-turn escalation24Encoding and obfuscation50Role-play and persuasion27Conversation structure manipulation11Reasoning-chain manipulation11Cross-modal payloads46Side channels3Defense-targeted30Dormant triggers27Selection manipulation3

Defense type

Detection and filtering3

Impact

Harmful content62Unauthorized actions5Data and privacy leaks5Output manipulation8

System type

Models and APIs75LLM applications11AI Agent20coding agent7

Attacker access

Black-box46White-box3

Attack surface / entry point

User input73Tool responses3Tool and skill descriptions5Code repositories and dependencies3Images, audio and video16Distribution channels5

Layer

Prompt layer71Application layer7

System component

MCP and skills5Guardrails and judges18Reasoning chains7Fine-tuning and open weights3Vision13Audio3Image generation7Multimodal21
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 technique：Encoding and obfuscationAttack technique：Role-play and persuasionAttack technique：Conversation structure manipulationSystem type：Models and APIsSystem type：coding agentClear all

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

  1. AttacksarXiv 2610.12644

    Cancerous backdoor attack: progressive activation via invisible tokens and a stage controller.

    Proposes the Cancerous backdoor, which progressively corrupts reasoning using invisible stage tokens.

    arXiv
    2610.12644
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Llama-3.1-8B-Instruct, Qwen2.5-7B-Instruct, Mistral-7B-Instruct-v0.3
    AbstractHidden tokens plus a stage controller make the backdoor progressively corrupt reasoning upon triggering, and the authors believe that looking only at the answer will miss it.

    Cancerous Backdoor Attack changes LLM backdoors from one-time activation to multi-stage reasoning corruption that accumulates progressively with triggers.

    Paper analysisRead analysis
  2. Evaluation and benchmarksarXiv 2610.11766

    研究提出意图恢复率作为 LLM 安全评测的补充指标

    提出 IRIS，用意图恢复率区分遮蔽越狱下无害输出的原因

    arXiv
    2610.11766
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    GPT-4o, Claude Sonnet 4.5, Claude Opus 4.5 and others6
    Abstract无害输出的证据权重取决于任务是否被恢复。

    IRIS 把意图恢复当作中间信号，用来解释意图遮蔽提示下为何没有出现有害协助。

    Paper analysisRead analysis
  3. Evaluation and benchmarksarXiv 2610.09033

    研究发布 ASRD 数据集，评测五款开源模型在非规范输入下的安全表现

    arXiv
    2610.09033
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Gemma 2 9B, Gemma 3 4B, Llama 3.1 8B and others6
    Abstract五模型、七族表面形式的四态评测里，低有害遵从不等于读懂后的安全处理。

    ASRD 用四态标签检查五个开源模型如何处理非规范表面上的有害请求。

    Paper analysisRead analysis
  4. AttacksarXiv 2610.02302

    研究者提出意图隐藏越狱的信息论框架，分析组合式攻击

    提出组合式意图隐藏越狱，按先验后验匹配选择辅助任务

    arXiv
    2610.02302
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3-1.7B, Qwen3-4B, Qwen3-8B and others7
    Abstract用信息论选含目标的任务组合，再看查询能否既隐藏意图又让目标被执行。

    这篇工作把组合式意图隐藏写成任务选择：有害目标必须留在 bundle 里，同时让估计的有害意图概率贴近全集先验，或降到阈值以下。

    Paper analysisRead analysis
  6. AttacksarXiv 2609.38253

    CollageAttack: Exploiting cross-modal alignment defects for spatial text composition jailbreaks against T2I models.

    提出 CollageAttack，用空间文本碎片重组越狱文生图模型

    arXiv
    2609.38253
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    GPT-Image-2, Doubao-Seedream-5.0-Lite, Wan2.7-Image-Pro and others5

    Abstract系统揭示 T2I 跨模态空间合成安全漏洞，证实离散无害元素可在图像层面重构有害意图并放大传播强度。

    Paper analysisRead analysis
  7. 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. Evaluation and benchmarksarXiv 2609.35912

    MMSkillRisk：多模态技能图像中的隐藏指令可诱导 Agent 执行未授权操作

    提出 MMSkillRisk 基准，评测多模态技能图像中的隐藏指令诱导 Agent 越权操作

    arXiv
    2609.35912
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GPT-5.6-sol, Kimi-K2.6, Kimi-K3 and others6

    Abstract论文提出 MMSkillRisk 基准与 NCVA 攻击，揭示多模态技能中教学图像潜藏指令可引发未授权操作并与良性任务共存。

    Paper analysisRead analysis
  11. 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 2609.18217

    研究：跨通道碎片化攻击可绕过 MCP 单通道防御

    提出跨通道分段攻击，利用 MCP 隐式信任外发敏感文件

    arXiv
    2609.18217
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GPT-4o, GPT-4o-mini, GPT-5.4 and others15

    Abstract论文揭示了 MCP 多通道隐式信任层级，通过跨通道分段与协议级利用突破现有防御，展示了严重的凭证外发风险。

    Paper analysisRead analysis
  15. AttacksarXiv 2609.09553

    研究：任意密文攻击前沿大模型无需微调即可越狱

    提出任意字母置换密码越狱，无需微调即可诱导有害输出

    arXiv
    2609.09553
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    Claude Sonnet 4, Claude Sonnet 4.5, Gemini 3 Flash (preview) and others7

    Abstract前沿大模型无需微调即可通过提示词学会字母置换密码，进而绕过分类器与对齐，作者呼吁关注能力提升带来的安全风险。

    Paper analysisRead analysis
  17. 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
  18. AttacksarXiv 2609.07216

    DIVA：利用视觉锚点对视频生成模型实施多模态越狱

    提出 DIVA，将有害意图拆成视觉锚点与运动文本以越狱视频生成模型

    arXiv
    2609.07216
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    Wan, CogVideoX, LTX-Video and others9
    AbstractDIVA 用视觉锚点抑制语义漂移做视频越狱，并给出多条件安全基准 TI2VSafetyBench。

    DIVA 是针对带参考图的视频生成模型的免训练 black-box 越狱：用一致性机制本身堵住语义漂移这条安全逃逸路径。。

    Paper analysisRead analysis
  19. Evaluation and benchmarksarXiv 2609.05843

    SinoGlyphBench：中文字形混淆下语言模型审核的诊断基准

    提出 SinoGlyphBench，用配对字形混淆诊断中文审核稳定性

    arXiv
    2609.05843
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    GPT-5.4 mini, GPT-5.5, DeepSeek V4 Flash and others12
    AbstractSinoGlyphBench 显示中文字形混淆会同时增加有害漏报和误报，全文扰动最重。

    SinoGlyphBench是一个配对诊断基准，用来看内容审核在可还原的中文字形混淆下是否还保持原决定。

    Paper analysisRead analysis
  20. 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
Load more