Skip to content

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

Oct 13 · Tuesday

All papers

Found 278 papers
Filter6

Attack type

Jailbreaks162Prompt injection12Poisoning and backdoors5Extraction and theft16Detection evasion23Denial of service4Malicious use6

Attack technique

Gradient and representation optimization39Automated search50Multi-turn escalation22Encoding and obfuscation45Role-play and persuasion24Conversation structure manipulation9Reasoning-chain manipulation10Cross-modal payloads48Side channels3Defense-targeted9Dormant triggers4

Model risks

Inappropriate refusal5

Defense type

Detection and filtering25Instruction–data separation6

Impact

Harmful content160Data and privacy leaks20Output manipulation60Availability and reliability10Oversight failure6

System type

Models and APIs266LLM applications8AI Agent13coding agent6Browser and computer use0Embodied systems and robotics6

Attacker access

Black-box104Gray-box6White-box18No-box (offline transfer)4

Attack surface / entry point

User input195Tool responses3Images, audio and video77Training data6Weights and gradients3Inference services and hardware13

Layer

Prompt layer257Model layer425Application layer162Training and data layer235Infrastructure layer21

System component

Guardrails and judges57Monitors5Reasoning chains15Fine-tuning and open weights4Vision60Audio11Video6Image generation18Multimodal91
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 201papers have no tags yet and are not included in filtered results.
System type：Models and APIsSystem type：coding agentSystem type：Browser and computer useSystem type：Embodied systems and roboticsLayer：Prompt layerLayer：Infrastructure layerClear all

Another 201papers 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. Analysis and theoryarXiv 2610.12313

    The study tests the sensitivity of five large-model compliance systems to perturbations of regulatory rules.

    Diagnose whether compliance system rulings change with perturbations to regulatory rules

    arXiv
    2610.12313
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Llama-3.3-70B-Instruct, Llama-3.1-8B-Instruct, Qwen2.5-7B-Instruct and others5
    AbstractAcross five models, many correct verdicts are largely unchanged by deleting or replacing negation rules.

    Use behavioral counterfactuals and activation probes to audit whether compliance rulings rely on the given rules. The authors aim to separate two kinds of seemingly identical correct rulings: those that use the given rules, and those obtained from case surface features or training patterns.

    Paper analysisRead analysis
  4. 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
  5. Evaluation and benchmarksarXiv 2610.11599

    研究：大语言模型版本更替削弱 AI 辅助科研写作筛查

    测量 LLM 版本更替对科学摘要 AI 改写检测器的影响

    arXiv
    2610.11599
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    RoBERTa-base, Pangram
    Abstract作者称检测器的基准准确率只是临时的，每次发布都要连同更早版本重验。

    作者量化的是：科学摘要的 AI 改写筛查，在 LLM 版本不断更换、而人类摘要误标必须少见时，会怎样变。问题来自期刊和会议已经按分数阈值筛查投稿，但基准多停在评估时可得的版本上。

    Paper analysisRead analysis
  6. Evaluation and benchmarksarXiv 2610.11112

    EpiReal-Bench：商用图像生成模型虚假声明红队基准

    构建 EpiReal-Bench，评测图像生成器将虚假主张渲染为可信证据

    arXiv
    2610.11112
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    GPT-Image-2, Nano Banana 2, Grok Imagen 2.0 and others4
    Abstract四款商用图像模型能把假主张画成可信证据。

    EpiReal-Bench 用来量商用图像生成器会不会把虚假现实主张画成可信视觉证据。

    Paper analysisRead analysis
  7. Evaluation and benchmarksarXiv 2610.10232

    研究：九种 LLM 说服力评测方法排名仅弱相关

    适配多种已发表说服评测并比较模型排名

    arXiv
    2610.10232
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Claude-Fable-5.1, GPT-5.6-Sol, Kimi-K2.6 and others15
    Abstract说服分数混合能力与意愿，换任务后同一模型的排名可以差很多。

    这项研究比较的是自动化说服评测是否一致，而不是哪一种分数更正确。

    Paper analysisRead analysis
  10. 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
  11. AttacksarXiv 2610.09027

    P-VMI：对抗图像经 KV cache 持续影响多轮对话

    提出持久视觉记忆注入，使对抗图像经缓存在触发时操控输出

    arXiv
    2610.09027
    Published
    Layer
    Infrastructure layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3-8B, Qwen3-VL-8B-Instruct, Gemma-4-12B

    Abstract论文提出 P-VMI，证实对抗输入被掩蔽后仍可经 KV 缓存持久控制模型，强调了保留状态的安全风险。

    Paper analysisRead analysis
  14. Evaluation and benchmarksarXiv 2610.07939

    CCDF dataset: Grok Imagine, Veo 3.1, Sora 2 forge surveillance footage, ten deepfake detectors basically cannot recognize it

    提出监控深伪基准 CCDF，在统一编码后评测检测器对伪造犯罪事故录像的识别

    arXiv
    2610.07939
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    C2P-CLIP, ForgeLens, D3-Im and others10

    Abstract提出消除格式捷径的监控深度伪造基准 CCDF，揭示现有检测器难以识别商用生成视频。

    Paper analysisRead analysis
  15. 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
  17. AttacksarXiv 2610.07323

    ATLAS：用自适应信任域与主动学习搜索潜在对抗样本集

    提出 ATLAS 用水平集估计恢复黑盒分类器的对抗输入集合

    arXiv
    2610.07323
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    LeNet5, ResNet50 (CIFAR-10 standard), ResNet50 (ImageNet standard) and others5
    AbstractATLAS 用主动水平集估计构造黑盒对抗集，作者称其集合比单点攻击更具代表性。

    ATLAS 是一个查询式 black-box 框架，用来构造诱发失败的对抗输入集合，供鲁棒性审计使用。

    Paper analysisRead analysis
  18. AttacksarXiv 2610.06848

    TranScope：利用 CPU 性能计数器对 Transformer 做成员推断攻击

    提出 TRANSCOPE，用 CPU 硬件计数器推断训练集成员

    arXiv
    2610.06848
    Published
    Layer
    Infrastructure layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    BERT (4.4M-340M), ViT (22M-307M), Pythia (70M-2.8B) and others5

    AbstractTRANSCOPE 揭示了分词器在嵌入表引发的硬件访问局部性差异，证实微架构计数器可突破恒定时间与置信度遮蔽防御。

    Paper analysisRead analysis
  20. Evaluation and benchmarksarXiv 2610.06496

    论文提出 Intent-Eval 基准，揭示多轮对话中模型混淆已否决意图

    提出 Intent-Eval 基准，测量多轮对话里模型对已否决意图的混淆

    arXiv
    2610.06496
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3.6-27B, Qwen3-8B, Qwen3-4B-Instruct-2507 and others10
    AbstractIntent-Eval 比较澄清、拒绝与修订。

    Intent-Eval 测的是多轮对话里，模型会不会只执行仍生效的要求。用户可以澄清、拒绝或接受变更。被提到后又失效的内容不该进入答案。

    Paper analysisRead analysis
Load more