Skip to content

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

Oct 12 · Monday

All papers

Found 228 papers
Filter4

Attack type

Jailbreaks220Prompt injection13Poisoning and backdoors20Model tampering26Extraction and theft4Detection evasion10Denial of service9Malicious use8

Attack technique

Gradient and representation optimization18Automated search43Multi-turn escalation22Encoding and obfuscation39Role-play and persuasion19Conversation structure manipulation9Reasoning-chain manipulation7Cross-modal payloads34Defense-targeted6

Model risks

Inappropriate refusal10

Defense type

Model hardening23Inference-time intervention15Detection and filtering19Instruction–data separation7Monitoring and auditing7

Impact

Harmful content227Unauthorized actions21Data and privacy leaks10Output manipulation11Availability and reliability1Oversight failure5

System type

Models and APIs206LLM applications4AI Agent18coding agent4science agent3Multi-agent systems3

Attacker access

Black-box102Gray-box4White-box29

Attack surface / entry point

User input215Tool responses7Images, audio and video49Training data4Weights and gradients7

Layer

Prompt layer155Model layer37Application layer18Training and data layer18

System component

Guardrails and judges47Monitors8Reasoning chains15Fine-tuning and open weights5Vision35Audio10Image generation20Multimodal64
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 useImpact：Harmful contentImpact：Availability and reliabilityClear 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. InterpretabilityarXiv 2610.13078

    Attention sees, MLP refuses: tracing the safety pathway from attention to MLP in LLMs

    Trace attention to identify harmfulness to the MLP refusal write pathway and propose Sentinel

    arXiv
    2610.13078
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Llama-3.1-8B-Instruct, Qwen2.5-7B-Instruct, Qwen3-8B-Instruct and others18
    AbstractAttention updates are more readable for harmfulness, MLP updates write refusal, and Sentinel routes alerts using two-path signals.

    The authors reframe jailbreaking and excessive refusal of aligned models as a pathway problem on the residual stream from recognition to writing, and accordingly provide conditional reminders before decoding.

    Paper analysisRead analysis
  5. Evaluation and benchmarksarXiv 2610.11766

    研究提出意图恢复率作为 LLM 安全评测的补充指标

    提出 IRIS，用意图恢复率区分遮蔽越狱下无害输出的原因

    arXiv
    2610.11766
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    GPT-4o, Claude Sonnet 4.5, Claude Opus 4.5 and others6
    Abstract无害输出的证据权重取决于任务是否被恢复。

    IRIS 把意图恢复当作中间信号，用来解释意图遮蔽提示下为何没有出现有害协助。

    Paper analysisRead analysis
  6. DefensesarXiv 2610.11005

    研究：叙事包装可跨语言绕过 LLM 拒答

    提出 GUISE 基准与 AXIS 训练，防御叙事包装越狱

    arXiv
    2610.11005
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3-1.7B, Qwen3-4B, GLM-4-9B
    AbstractGUISE 分开测包装与语域。

    作者测量叙事包装下的拒答失效，并训练一个在未见包装上拒绝、同时仍回答同风格良性请求的适配器。问题是：安全对齐模型拒绝直说的有害请求，却回答嵌进角色或叙事里的同一请求。文言文被用来把语域和包装拆开。

    Paper analysisRead analysis
  7. Evaluation and benchmarksarXiv 2610.10276

    PatchBench 提出激活补丁局部评测协议，揭示越狱修复的附带损伤

    提出 PatchBench-Local 协议，评测激活补丁修复越狱的局部附带损伤

    arXiv
    2610.10276
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Qwen2.5-3B-Instruct, Qwen2.5-14B-Instruct, gemma-3-4b-it and others8

    Abstract论文提出 PatchBench 与局部评估协议，揭示了激活补丁在全局能力无损下仍存局部良性退化。

    Paper analysisRead analysis
  10. 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
  11. DefensesarXiv 2610.09167

    Persist-3 用顺序检验识别未见越狱来源，提升 MTK 与 Prompt Guard 2 防御效果

    提出 Persist-3 序贯检验，从隐藏表示识别未见越狱源

    arXiv
    2610.09167
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Llama2-7B-chat, Qwen2.5-7B-Instruct, Gemma-2-9B-it and others4
    AbstractPersist-3 用有限窗口检验攻击流是否超出已知越狱源，检出率低于全历史 SR-DKW，但决策只依赖最近观测。

    Persist-3 是一个有限记忆的序贯检测器，用来判断攻击表示流是否已经不能由任何一个已知越狱源解释。。

    Paper analysisRead analysis
  12. Evaluation and benchmarksarXiv 2610.09033

    研究发布 ASRD 数据集，评测五款开源模型在非规范输入下的安全表现

    arXiv
    2610.09033
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Gemma 2 9B, Gemma 3 4B, Llama 3.1 8B and others6
    Abstract五模型、七族表面形式的四态评测里，低有害遵从不等于读懂后的安全处理。

    ASRD 用四态标签检查五个开源模型如何处理非规范表面上的有害请求。

    Paper analysisRead analysis
  13. DefensesarXiv 2610.08678

    研究揭示投机解码的安全代价并提出 SecureSD 加固方法

    测量有损投机解码的安全代价，并提出 SecureSD 收紧早期验证

    arXiv
    2610.08678
    Published
    Layer
    Model layer
    Setting
    AI Agent
    Attacker
    Black-box
    Evaluated models
    Qwen3-8B, Qwen3-32B, Llama-3.1-8B-Instruct and others6
    Abstract有损推测解码的早期偏离更快抬高越狱与注入风险。

    作者研究有损推测解码在换取速度时，是否会比效用更快地损害越狱与提示注入防护，并给出按位置校正的 SecureSD。

    Paper analysisRead analysis
  14. DefensesarXiv 2610.07532

    LADE：用暗知识中的模型无关潜在安全信号防御 LLM 越狱

    提出 LADE，用首 token 暗知识在生成前过滤越狱查询

    arXiv
    2610.07532
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    White-box
    Evaluated models
    Llama-2-7B-Chat, Llama-3-8B-Instruct, Qwen2-7B-Instruct and others13
    Abstract作者用 LADE 在生成前过滤有害查询，并称八个模型中六个的 Held-out 平均最好。

    LADE 是一种只读首 token 输出概率的防御，用来在生成前挡下可能引出有害回复的查询。

    Paper analysisRead analysis
  15. DefensesarXiv 2610.07276

    SAFESHIELD：小语言模型部署时安全的决策组织框架

    提出 SAFESHIELD，组织小语言模型部署时的安全决策

    arXiv
    2610.07276
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    Qwen3-4B-Instruct
    AbstractSAFESHIELD 用可审计决策轨迹组织 SLM 部署时的四项安全决策，并报告协调依赖影响端到端结果。

    SAFESHIELD 是面向小语言模型的部署时安全框架，把运行时安全从单项审核改写成可检查的决策过程。

    Paper analysisRead analysis
  16. AttacksarXiv 2610.07125

    PEV 攻击利用嵌入向量加噪越狱六款开源权重模型

    提出 PEV 攻击，在输入嵌入上加高斯噪声越狱开源模型

    arXiv
    2610.07125
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Llama-3.1-8B-Instruct, Qwen2.5-1.5B-Instruct, Phi-4-mini-3.8B and others6
    AbstractPEV 用 embedding 高斯噪声，在六个模型上越狱 JailbreakBench 全部提示。

    PEV 是对 open-weight LLM 的 embedding 噪声越狱。

    Paper analysisRead analysis
  17. AttacksarXiv 2610.06670

    研究者提出 Reward Stealing Attack，从对齐模型行为反推安全奖励实施攻击

    提出 ReSA，从对齐模型行为恢复安全奖励并在解码时反转

    arXiv
    2610.06670
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Attacker
    White-box, Gray-box
    Evaluated models
    Llama3.1-8B-Instruct, Gemma-7B-Instruct, Qwen2.5-7B-Instruct and others9
    AbstractReSA 用最大熵 IRL 从对齐模型行为恢复代理安全奖励，并在解码时反转以诱导有害输出。

    ReSA 是一种对抗攻击：从对齐模型的可观察行为恢复代理安全奖励，再在解码时把该奖励反过来用。。

    Paper analysisRead analysis
  19. Evaluation and benchmarksarXiv 2610.07089

    研究者提出统一滥用监控基准，覆盖分解攻击与提示注入约 6200 条轨迹

    提出危害窗口与区间指标，统一评测分解攻击和提示注入下的智能体滥用监视

    arXiv
    2610.07089
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Gemma 4 26B-A4B, Qwen3.6 27B, Qwen3.5 27B and others12

    Abstract统一智能体滥用监视框架，动作视角兼顾两类威胁但危害定位仍存瓶颈。

    Paper analysisRead analysis
  20. DefensesarXiv 2610.05401

    AVCE：面向扩散模型可验证概念擦除的审计感知遗忘框架

    提出审计感知遗忘框架 AVCE，从文本与视觉通路擦除扩散模型概念

    arXiv
    2610.05401
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Attacker
    White-box, Black-box
    Evaluated models
    Stable Diffusion XL (SDXL), Stable Diffusion v1.5 (SD v1.5), Flux 1.0
    AbstractAVCE 在审计锚点上改两条注意力通路。

    AVCE 是面向扩散模型的概念擦除方法，要让擦除经得起绕过文本条件的潜空间审计，而不只是挡住对抗提示词。

    Paper analysisRead analysis
Load more