Skip to content

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

Oct 13 · Tuesday

All papers

Found 15 papers
Filter6

Attack type

Jailbreaks12Detection evasion3

Attack technique

Gradient and representation optimization3Automated search15Multi-turn escalation4Encoding and obfuscation15Role-play and persuasion4Reasoning-chain manipulation3Cross-modal payloads9Defense-targeted18Dormant triggers5

Impact

Harmful content14

System type

Models and APIs14LLM applications5AI Agent1coding agent0Browser and computer use0

Attacker access

Black-box11

Attack surface / entry point

User input15Images, audio and video5

Layer

Prompt layer13

System component

MCP and skills7Memory3Guardrails and judges15Vision14Image generation7Multimodal21
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 215papers have no tags yet and are not included in filtered results.
Attack technique：Encoding and obfuscationSystem type：Models and APIsSystem type：AI AgentSystem type：coding agentSystem type：Browser and computer useSystem component：Guardrails and judgesClear all

Another 215papers do not have category tags yet and are not included in filtered results.

  1. 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
  2. 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
  3. 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
  4. 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
  5. 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
  7. AttacksarXiv 2606.21077

    OTTER：仅替换五个 token 即可绕过 GPT 系列毒性审核

    提出 OTTER 词元替换越狱，绕过表面毒性审核诱导有害回答

    arXiv
    2606.21077
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    gpt-4-turbo, gpt-4o, gpt-4o-mini and others4

    Abstract论文展示了表面毒性与恶意意图的解耦现象，通过标准 API 实现黑盒越狱测试，并提出闭环分类器加固建议。

    Paper analysisRead analysis
  8. AttacksarXiv 2606.01837

    论文提出 DSR 跨模态越狱框架：用良性输入诱导 MLLM 有害输出

    提出 DSR 跨模态越狱，用无害图文诱导 MLLM 生成有害图像

    arXiv
    2606.01837
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    gemini-2.5-flash-image, qwen-image-2.0, Tongyi Wanx 2.5
    AbstractDSR 用无害图文诱导商业 MLLM 输出有害图像，作者称组合能力会反过来扩大攻击面。

    DSR 是一种 black-box 跨模态越狱：输入侧不放显式有害内容，而让商业 MLLM 在推理中把无害图文重组成有害图像。

    Paper analysisRead analysis
  11. AttacksarXiv 2603.07028

    Two frames suffice: a temporal attack for jailbreaking text-to-video models

    Propose TFM, using start and end frames and implicit substitution to jailbreak text-to-video models

    arXiv
    2603.07028
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    Pixverse V5, Hailuo 02, Kling 2.1 Master and others4
    AbstractTFM first extracts start and end frames and then performs implicit substitution.

    TFM is a strictly black-box prompt jailbreak for text-to-video that exploits the model's temporal infilling of unspecified intermediate processes.

    Paper analysisRead analysis
You have reached the end