Skip to content

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

Oct 12 · Monday

Jailbreaks and attacks · Papers

Found 23 papers
Filter3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
  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

    Published
    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. 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

    Published
    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
  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

    Published
    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
  4. AttacksarXiv 2605.07399

    研究者提出 GPO-V,用全局概率优化越狱扩散视觉语言模型

    提出 GPO-V,用全局概率优化的视觉扰动越狱扩散视觉语言模型

    Published
    Evaluated models
    LLaDA-V, LaViDA
    Abstract作者用视觉扰动改 dVLM 的全局生成概率,以绕过两类拒绝。

    GPO-V 把越狱从“开头必须顺从”改成“整段去噪概率朝肯定方向走”。。

    Paper analysisRead analysis
  5. AttacksarXiv 2605.00583

    Jailbreaking vision-language models through the visual modality

    提出四类视觉越狱,把有害意图编码进图像以绕过安全拒答

    Published
    Evaluated models
    GPT-5.2, Claude-Haiku-4.5, Gemini-3-Flash and others8
    Abstract四类视觉越狱在六个 VLM 上检验文本对齐能否挡住视觉意图,模型与攻击之间差异大。

    四类视觉越狱用来检验前沿 VLM 的文本安全训练能否挡住由图像传达的有害意图。。

    Paper analysisRead analysis
  6. AttacksarXiv 2603.07590

    Model as Lego builder: assembling malicious content from harmless blocks using a semantic blueprint

    Propose StructAttack, which uses structural diagrams to induce visual models to assemble malicious content from harmless semantic slots.

    Published
    Attacker
    Black-box
    Evaluated models
    GPT-4o (1120), Gemini-2.0-Flash (001), Gemini-2.5-Flash and others6
    AbstractStructAttack decomposes a harmful query into harmless slots and draws them into a structure graph, inducing the LVLM to fill in harmful content under a black-box single query.

    StructAttack is a black-box, single-query jailbreak against LVLMs: it decomposes a harmful instruction into separate seemingly harmless slots, draws them into a structural diagram, and then makes the model reassemble the slots into harmful content.

    Paper analysisRead analysis
  7. 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

    Published
    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
  8. AttacksarXiv 2602.10148

    Red-Teaming Multimodal Reasoning: Cross-Modal Entanglement Attacks Jailbreak Vision-Language Models

    提出 COMET 跨模态纠缠攻击,越狱视觉语言模型

    Published
    Attacker
    Black-box
    Evaluated models
    GPT-4.1, GPT-4.1-mini, Gemini-2.5-Flash and others9
    AbstractCOMET 做黑盒跨模态纠缠越狱。

    COMET 是面向具备多模态推理的 VLM 的黑盒越狱,用来红队测试跨模态安全对齐。作者要处理的缺口是:把恶意线索分到图文的固定组合,测不到多步推理里才出现的漏洞。攻击不访问梯度,只构造图文输入。

    Paper analysisRead analysis
  9. AttacksarXiv 2601.15698

    Beyond Visual Safety: Jailbreaking Multimodal Large Language Models to Generate Harmful Images with Semantically Irrelevant Inputs

    提出 BVS 图文越狱,用中和拼接图和诱导提示词让模型生成有害图像

    Published
    Evaluated models
    GPT-5 (12 January 2026 release), Gemini 1.5 Flash (15 January 2026 release)
    AbstractBVS 以重建后再生成诱导有害图像。

    BVS 用图文对诱导 MLLM 生成有害图像。作者认为,相对文本越狱和单模态图像诱导,视觉生成的安全审查仍不充分。

    Paper analysisRead analysis