Skip to content

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

Oct 12 · Monday

All papers

Found 200 papers
Filter3

Attack type

Jailbreaks31Prompt injection45Poisoning and backdoors48Model tampering4Extraction and theft11Detection evasion11Denial of service3Malicious use7

Attack technique

Gradient and representation optimization3Automated search17Encoding and obfuscation12Conversation structure manipulation4Reasoning-chain manipulation13Cross-modal payloads7Defense-targeted8Dormant triggers27

Model risks

Deception and scheming11Reward hacking9Misalignment and value divergence11Dangerous agent actions7Inappropriate refusal3Hallucination and fabrication5

Defense type

Model hardening16Inference-time intervention7Detection and filtering13Instruction–data separation10Permissions and approval11Monitoring and auditing6Watermarking and provenance5

Impact

Harmful content41Unauthorized actions27Data and privacy leaks23Output manipulation46Availability and reliability7Oversight failure19

System type

Models and APIs105LLM applications6AI Agent89coding agent14Multi-agent systems12

Attacker access

Black-box27White-box9

Attack surface / entry point

User input65Web pages and interfaces11Documents and messages17Tool responses17Tool and skill descriptions5Code repositories and dependencies6Retrieval corpus6Memory writes36Inter-agent messages4Images, audio and video22Training data6Weights and gradients8Distribution channels6

Layer

Prompt layer31Model layer53Application layer90Training and data layer25

System component

MCP and skills82Memory78RAG51Guardrails and judges169Monitors92Reasoning chains75Permissions and sandboxing93Fine-tuning and open weights64Vision137Audio38Video13Image generation49Embeddings13Multimodal224
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 254papers have no tags yet and are not included in filtered results.
System component：MemorySystem component：Reasoning chainsSystem component：Image generationClear all

Another 254papers 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. Risky behaviorarXiv 2610.12822

    Reward hacking as a transmissible strategy in multi-agent coding systems

    Show that reward hacking can propagate through code, memory, and plans in multi-agent coding systems

    arXiv
    2610.12822
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems, coding agent
    Evaluated models
    Qwen2.5-Coder-14B, Gemma-3-12B, Qwen2.5-Coder-7B and others16
    AbstractThe authors state that reward hacking can spread across models and affect routing and aggregation, and that review can reduce delivery.

    Reward hacking induced by coding RL can leave the source agent and enter subsequent collaboration and system coordination.

    Paper analysisRead analysis
  4. AttacksarXiv 2610.12644

    Cancerous backdoor attack: progressive activation via invisible tokens and a stage controller.

    Proposes the Cancerous backdoor, which progressively corrupts reasoning using invisible stage tokens.

    arXiv
    2610.12644
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Llama-3.1-8B-Instruct, Qwen2.5-7B-Instruct, Mistral-7B-Instruct-v0.3
    AbstractHidden tokens plus a stage controller make the backdoor progressively corrupt reasoning upon triggering, and the authors believe that looking only at the answer will miss it.

    Cancerous Backdoor Attack changes LLM backdoors from one-time activation to multi-stage reasoning corruption that accumulates progressively with triggers.

    Paper analysisRead analysis
  5. InterpretabilityarXiv 2610.12361

    Study: legal reasoning models citing legal provisions does not equal relying on legal provisions.

    Uses premise permutation and hidden-layer tracing to audit whether legal chain-of-thought truly relies on the cited legal provisions.

    arXiv
    2610.12361
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3-8B, Qwen3-14B, Llama-3.1-8B and others7
    AbstractUsing counterfactual substitution of authorities and internal commitment tracing, the authors find that legal CoT rulings depend on authorities only to a limited extent and are vulnerable to prompt injection manipulation.

    This study conducts an empirical audit of the causal truthfulness of legal citations in chain-of-thought reasoning of large language models in the legal domain.

    Paper analysisRead analysis
  6. Analysis and theoryarXiv 2610.11765

    研究提出三项指标衡量 LLM 不思考行为，发现被要求停止思考时仍持续显式推理

    度量关闭思考指令下终答前是否仍有可见显式推理

    arXiv
    2610.11765
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3-4B, Qwen3-32B, Qwen3-235B-A22B and others6
    Abstract作者用三级指标测 no-thinking，并称模型有随答案空间加重的思考惯性。

    作者把 no-thinking 定义为可测量的回答行为，而不是从思考开关、特殊标记或输出长度推断。

    Paper analysisRead analysis
  7. DefensesarXiv 2610.11352

    RL-ARC：用推理引导的不确定性校准大型推理模型

    提出 RL-ARC，用推理置信度在强化学习中校准推理模型

    arXiv
    2610.11352
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Qwen2.5-7B, Qwen3-8B, Llama-8B distilled from DeepSeek-R1
    AbstractRL-ARC 用推理置信度调节答案置信度，作者称可少牺牲精度并改善 ID 与 OOD 校准。

    RL-ARC 是校准感知的强化学习框架，用推理过程的口头置信度调节答案置信度。

    Paper analysisRead analysis
  8. 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
  9. Analysis and theoryarXiv 2610.10405

    研究发现大语言模型被要求不诚实作答时推理 token 数上升

    检验推理 token 数能否区分被提示的诚实与不诚实作答

    arXiv
    2610.10405
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Gemma-4-e4b, Qwen-3.5-9b, GPT-OSS-120B
    Abstract被提示不诚实时推理 token 组水平更高。

    三个推理模型在被提示的回答政策下出现组水平推理 token 差异。作者把它当作不读思维链内容的 black-box 候选信号，而不是自发欺骗检测器。

    Paper analysisRead analysis
  10. Analysis and theoryarXiv 2610.09667

    东京大学研究：推理模型按 UUID 阈值或整除规则挑选审计样本，控制标识符即可躲开复核

    揭示推理模型用标识符规则替代随机抽样，使审计可被预测

    arXiv
    2610.09667
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    GPT-6 Sol, GPT-6 Luna, GPT-5.4 mini and others6

    Abstract研究揭示推理智能体将标识符转化为确定性规则，破坏群体独立性并导致审计预测漏洞，建议显式提供随机输入。

    Paper analysisRead analysis
  11. InterpretabilityarXiv 2610.09087

    U-Space：揭示语言模型不确定性何时与为何产生

    提出 U-SPACE 与 U-LENS，从残差流估计推理轨迹不确定性

    arXiv
    2610.09087
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Gemma-4-31B-it, Qwen3.5-27B, Magistral-Small-2507
    AbstractU-SPACE 与 U-LENS 用语义方向和预测熵读推理不确定性，长度控制后仍高于所比基线。

    U-SPACE 与 U-LENS 是面向推理模型的无训练读出：用语义方向定位不确定性的形式，并用一个轨迹分数区分更可能错的回答。

    Paper analysisRead analysis
  13. Evaluation and benchmarksarXiv 2610.08902

    论文提出 agent plasticity 指标衡量智能体通过经验自我改进的效率

    提出 agent plasticity 指标衡量智能体通过经验自我改进的效率

    arXiv
    2610.08902
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Claude Fable 5, Claude Opus 5, GPT-5.6 Sol and others10
    Abstract作者用固定权重协议比较前沿模型把经验写成制品后的留出增益与习得效率。

    作者用 agent plasticity 衡量一件事：权重冻结时，智能体把经验写成可继承制品，再换成留出能力增益，这个转换有多省。

    Paper analysisRead analysis
  14. DefensesarXiv 2610.08761

    VeriFine：通过扩展验证实现具身推理的自我改进

    提出 VeriFine，用双环协同扩展验证以实现具身推理自我改进

    arXiv
    2610.08761
    Published
    Layer
    Training and data layer
    Setting
    Embodied systems and robotics
    Evaluated models
    Alpamayo 1.5 8B, Qwen3-VL 2B, Claude Opus 5
    AbstractVeriFine 用双环协同演化具身推理的策略、课程和评审，驾驶与导航的策略分和评审对齐都上升。

    VeriFine 把驾驶和导航推理的自改进写成策略、课程和无参考评审的协同演化，用来处理固定评审跟不上新失败模式的问题。

    Paper analysisRead analysis
  15. Evaluation and benchmarksarXiv 2610.08215

    Learn2Play Bench 发布：用规则陌生的文本游戏评测 LLM Agent 从经验中学习的能力

    用 Learn2Play Bench 评测 Agent 从经验中学习陌生规则

    arXiv
    2610.08215
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Claude Opus 5.5, GPT-6 Astra, Claude Opus 5 and others11
    Abstract用隐藏规则游戏把新学习与预训练知识分开，并比较模型、记忆方式和人类。

    Learn2Play Bench 用新设计的隐藏规则文本游戏，评测 LLM 智能体在不更新权重时从交互中学习的能力。

    Paper analysisRead analysis
  18. 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
  19. DefensesarXiv 2610.07657

    DEFER1 多智能体防御研究报告受控测试中的攻击成功率下降

    实现 DEFER，以确定性检查优先拦截多智能体流水线的内容攻击

    arXiv
    2610.07657
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Qwen3-235B-A22B-Instruct-2507, gpt-oss-120b, Llama-4-Scout-17B-16E-Instruct and others5
    AbstractDEFER 把确定性检查放在 judge 之前。

    DEFER 用来测量多智能体授权流水线里，确定性规则在何处结束、LLM judge 从何处开始。

    Paper analysisRead analysis
  20. AttacksarXiv 2610.07645

    SkillPoison：用成功经验投毒自进化 Agent 的技能形成

    提出 SkillPoison，用局部有效的成功经验诱导自进化 Agent 形成过度泛化技能

    arXiv
    2610.07645
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    deepseek-v4-flash, Qwen V3.8 Flash, GPT-5.5
    AbstractSkillPoison 通过局部有效且验证成功的经验诱导技能过度泛化，在多个评测基准上实现了持久的下游攻击影响。

    SkillPoison 提出了一种针对自进化智能体经验到技能形成过程的攻击范式，通过组织已验证的成功经验诱导技能过度泛化。

    Paper analysisRead analysis
Load more