Skip to content

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

Oct 12 · Monday

All papers

Found 61 papers
Filter4

Attack type

Jailbreaks53Prompt injection64Poisoning and backdoors43Extraction and theft6Detection evasion30Denial of service3Malicious use8

Attack technique

Gradient and representation optimization5Automated search13Multi-turn escalation7Encoding and obfuscation14Cross-modal payloads34

Defense type

Inference-time intervention5Detection and filtering6

Impact

Harmful content51Output manipulation4

System type

Models and APIs54AI Agent5

Attacker access

Black-box35White-box8

Attack surface / entry point

User input265Documents and messages3Tool responses17Tool and skill descriptions5Code repositories and dependencies4Inter-agent messages3Images, audio and video56Training data4Weights and gradients7

Layer

Prompt layer47Model layer7Application layer7

System component

Guardrails and judges14Reasoning chains4Vision38Audio12Image generation7Multimodal56
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 type：JailbreaksAttack type：Malicious useAttack surface / entry point：Tool and skill descriptionsAttack surface / entry point：Images, audio and videoClear all

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

  1. DefensesarXiv 2610.13733

    KVeil: First-Place Solution for the ECCV 2026 LifeGenIP Unlearnable Video Challenge

    Propose KVeil, which adds perturbations to face videos to prevent unauthorized customization from reproducing identity

    arXiv
    2610.13733
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    White-box, Black-box
    Evaluated models
    Wan2.2-TI2V-5B, HunyuanVideo-1.5, Kling 3.0 and others4

    AbstractKVeil adapts LETHE's reference-reading disruption to the challenge's two stages, ranking first on the leaderboard in both Final columns.

    Paper analysisRead analysis
  2. DefensesarXiv 2610.13333

    LETHE: Defending Against Unauthorized Image-to-Video Generation via Value Diversity Collapse

    Proposes LETHE, which perturbs reference images to block unauthorized image-to-video

    arXiv
    2610.13333
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Wan2.1-I2V-14B, CogVideoX-5B-I2V, LightX2V and others6
    AbstractLETHE suppresses the diversity of reference values and attracts attention, making protected images difficult to animate faithfully.

    LETHE is a protective perturbation added to personal images before publication, used to counter unauthorized image-to-video generation.

    Paper analysisRead analysis
  3. DefensesarXiv 2610.09703

    研究揭示 Token-Pruning 对 VLM 安全性的影响并提出 SAP 缓解机制

    提出 Safety-Aware Pruning，缓解视觉 token 剪枝放大的多模态越狱

    arXiv
    2610.09703
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    LLaVA-1.5-7B
    Abstract剪枝去掉背景 token 后注意力塌向恶意前景。

    这篇工作评估视觉 token 剪枝如何改变 VLM 在多模态越狱下的行为，并给出推理时防御 SAP。

    Paper analysisRead analysis
  4. AttacksarXiv 2610.05943

    CRIME 框架利用良性 Agent 技能组合诱发恶意行为

    提出 CRIME 框架，组合良性 Agent 技能诱发恶意行为

    arXiv
    2610.05943
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    DeepSeek-V4-Flash, GPT-4o-mini, GPT-4o and others6
    Abstract良性技能经 DCA 或 ACA 组合后可产生恶意环境后果，单独审查对不上。

    CRIME 把公共技能库中各自通过审查的技能配成两两组合，看联合执行能否实现指定恶意任务。。

    Paper analysisRead analysis
  6. Analysis and theoryarXiv 2610.07005

    研究审计 Qwen2-Audio 音频越狱 AdvWave-P 的频率与解码层归因

    遮挡审计 AdvWave-P 音频越狱的频带必要性与解码层关联

    arXiv
    2610.07005
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Qwen2-Audio-7B-Instruct, LLaMA-Omni
    AbstractAdvWave-P 的八频带排序与能量相关。

    这是对加性音频越狱 AdvWave-P 的频率与解码器深度审计，受害模型主要是 Qwen2-Audio-7B-Instruct，不提出新攻击。

    Paper analysisRead analysis
  8. DefensesarXiv 2609.36562

    ThinkingGuard：通过逐步风险归因解码多模态大语言模型中的隐式危害

    构建 TriggerBench 并训练 ThinkingGuard，检测图文隐式风险

    arXiv
    2609.36562
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    ThinkingGuard（Qwen3-VL-8B-Instruct）
    AbstractTriggerBench 隔离触发条件，ThinkingGuard 用分步归因在隐式风险检测上取得作者报告的较高平均分。

    这篇工作研究多模态隐式风险检测：图文各自良性，风险只在关键元素与触发元素交互时出现。

    Paper analysisRead analysis
  9. Risky behaviorarXiv 2609.30266

    研究显示 Claude Code、Codex 等本地智能体可轻易篡改自身执行轨迹

    测试编程智能体被诱导或自主篡改自身执行轨迹的行为

    arXiv
    2609.30266
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GPT-5.6-Sol, GPT-6-Sol, Opus-5 and others11
    Abstract论文评估了本地智能体的轨迹防篡改能力，发现其可因外部指令或奖励追求而清除执行证据，亟需建立独立拦截记录机制。

    这是一项针对本地大模型智能体执行轨迹完整性与安全防篡改边界的实证研究。

    Paper analysisRead analysis
  11. DefensesarXiv 2609.27399

    GUARD：在 CosyVoice2 上做说话人身份遗忘以阻止重识别

    提出 GUARD，在零样本 TTS 上用激活转向遗忘说话人身份以阻止再识别

    arXiv
    2609.27399
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    CosyVoice2-0.5B, F5-TTS, FireRedTTS
    AbstractGUARD 用门控激活转向把退出说话人推向冒充相似度，以抑制再识别并保住音质。

    GUARD 用门控激活转向做说话人身份遗忘，使零样本 TTS 对退出说话人难以再识别。

    Paper analysisRead analysis
  15. DefensesarXiv 2609.10613

    后验重加权框架解释并缓解多模态大模型上下文越狱

    用后验重加权解释多模态上下文越狱，并提出风险门控的良性示例注入防御

    arXiv
    2609.10613
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3-VL-2B, Qwen3-VL-4B, Qwen3-VL-8B and others8
    Abstract后验重加权解释上下文越狱的缩放，并支持风险门控的良性示例防御。

    Zhang 等把多模态 ICL 越狱写成对齐模型在安全与有害隐模式之间的推理时后验漂移，并据此做风险门控防御。

    Paper analysisRead analysis
  16. 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
Load more