Skip to content

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

Oct 12 · Monday

All papers

Found 34 papers

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

  1. 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

    Published
    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
  2. 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
  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

    Published
    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

    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
  5. 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

    Published
    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
  6. 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
  7. AttacksarXiv 2605.03441

    研究用数学编码绕过 LLM 安全过滤

    提出 Formal Logic 等数学编码越狱,绕过自然语言安全过滤

    Published
    Attacker
    Black-box
    Evaluated models
    GPT-4o-Mini, GPT-5-Mini, GPT-5 and others8
    Abstract作者比较六种数学编码,称深度改写而非数学符号本身更能绕过现有安全过滤。

    作者在 black-box、只提交纯文本的设定下,比较六种数学编码能否让仍开着安全措施的模型产出有害内容。

    Paper analysisRead analysis
  8. 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
  9. AttacksarXiv 2603.10091

    Multi-Stream Perturbation Attack: Breaking the Safety Alignment of Reasoning LLMs through Concurrent Task Interference

    提出多流扰动攻击,交织有害与良性任务绕过思考型 LLM 安全对齐

    Published
    Evaluated models
    Qwen3 1.7B, Qwen3 4B, Qwen3 8B and others11
    Abstract多流扰动用任务交织测试 thinking 模式,作者称它同时冲击内容安全与推理稳定性。

    多流扰动攻击把有害任务与良性任务织进同一提示词,测试 thinking 模式的内容安全与推理稳定性。作者认为,交织多任务会拉长思考,使安全检测面对被打散的有害意图,并可能把推理用于合理化,或陷入崩溃与重复。方法不访问梯度。

    Paper analysisRead analysis
  10. 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
  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

    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
  12. AttacksarXiv 2603.01414

    Jailbreaking embodied LLMs via action-level manipulation

    Propose Blindfold, jailbreaking embodied LLMs with action-level manipulation

    Published
    Evaluated models
    Llama-3.1-8B, DeepSeek-R1-14B, Gemma-3-27B and others8
    AbstractBlindfold jailbreaks embodied LLMs with action-level proxy planning, and the authors claim it can bypass semantic checks and is effective in both simulation and real-world settings.

    Blindfold is a no-box attack against embodied LLM planning modules, rewriting malicious intent into seemingly benign action sequences.

    Paper analysisRead analysis