Skip to content

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

Oct 12 · Monday

All papers

Found 6 papers
Filter4

Attack type

Jailbreaks5

Attack technique

Gradient and representation optimization1Encoding and obfuscation5Cross-modal payloads9

Impact

Harmful content5

System type

Models and APIs5

Attacker access

Black-box5

Attack surface / entry point

User input18Images, audio and video6

Layer

Prompt layer5

System component

Guardrails and judges6Vision38Audio5Image generation3Multimodal46
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 232papers have no tags yet and are not included in filtered results.
Attack technique：Gradient and representation optimizationAttack technique：Encoding and obfuscationAttack surface / entry point：Images, audio and videoSystem component：Guardrails and judgesClear all

Another 232papers do not have category tags yet and are not included in filtered results.

  1. 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
  2. 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
  3. 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
  6. AttacksarXiv 2511.16110

    MFA 框架在 17 个视觉语言模型上取得 58.5% 攻击成功率

    提出 MFA 框架，协同突破视觉语言模型的对齐、提示与审核层

    arXiv
    2511.16110
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    MiniGPT-4, LLaMA-4-Scout-Inst, LLaMA-3.2-11B-Vision-Instruct and others17

    Abstract作者称多层防御的 VLM 仍存在跨模型漏洞，MFA 整合三项技术实现了端到端越狱。

    Paper analysisRead analysis
You have reached the end