Skip to content

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

Oct 12 · Monday

All papers

Found 123 papers
Filter2

Attack type

Jailbreaks4Prompt injection25Poisoning and backdoors14Extraction and theft3

Attack technique

Gradient and representation optimization8Automated search4Cross-modal payloads3Dormant triggers6

Model risks

Deception and scheming12Reward hacking7Misalignment and value divergence8Dangerous agent actions15Inappropriate refusal4Hallucination and fabrication3

Defense type

Model hardening8Inference-time intervention4Detection and filtering5Instruction–data separation4Permissions and approval9Monitoring and auditing4

Impact

Harmful content9Unauthorized actions25Data and privacy leaks7Output manipulation30Availability and reliability13Oversight failure10

System type

Models and APIs853LLM applications136AI Agent644coding agent135science agent32web agent34Browser and computer use19Multi-agent systems77Embodied systems and robotics47

Attack surface / entry point

User input16Documents and messages6Tool responses6Tool and skill descriptions3Retrieval corpus3Memory writes6Inter-agent messages24Images, audio and video8Training data5Weights and gradients3Distribution channels3

Layer

Prompt layer6Model layer11Application layer92Training and data layer14

System component

MCP and skills4Memory11Guardrails and judges8Monitors10Permissions and sandboxing12Fine-tuning and open weights3Vision11Multimodal13
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 281papers have no tags yet and are not included in filtered results.
System type：Multi-agent systemsSystem type：Embodied systems and roboticsClear all

Another 281papers do not have category tags yet and are not included in filtered results.

  1. OtherarXiv 2610.13479

    A local agentic AI framework generates edge-case scenarios for safety assurance

    Proposes a local dual-model closed loop to generate edge scenarios for autonomous system safety assurance

    arXiv
    2610.13479
    Published
    Layer
    Application layer
    Setting
    LLM applications, Embodied systems and robotics
    Evaluated models
    PPO
    AbstractLocal closed-loop generation of JSON edge cases.

    The authors built a local agentic loop that runs on a laptop to generate edge cases for safety arguments of autonomous systems, rather than releasing a new public test set.

    Paper analysisRead analysis
  3. OtherarXiv 2610.13372

    Toward Safe World Models: Risks, Defenses, and Evaluation

    A survey of risks, defenses, and evaluation in the six-stage lifecycle of world models

    arXiv
    2610.13372
    Published
    Layer
    Application layer
    Setting
    Embodied systems and robotics
    AbstractSafety is written as a property of the prediction-decision closed loop; claims must be linked to observed consequences and versions.

    World model safety is organized by the nature of the prediction-decision loop, not by isolated prediction scores.

    Paper analysisRead analysis
  4. 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
  5. Analysis and theoryarXiv 2610.12436

    The study proposes an ecological theory of AI agent populations: collaboration brings a critical scale for takeoff.

    An ecological model is established for a population of mismatched agents, showing that collaboration produces a critical takeoff scale.

    arXiv
    2610.12436
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    AbstractThe authors say that collaboration changes takeoff from an individual capability threshold to a population threshold, so small-population evaluations are insufficient.

    The authors use the ecological strong Allee effect to discuss whether a mismatched agent population can take off when individual capabilities remain unchanged..

    Paper analysisRead analysis
  6. DefensesarXiv 2610.12432

    FAITH: A feasibility-aware safety filtering reinforcement learning framework for high-dimensional systems

    Proposes the FAITH safe filtering reinforcement learning framework, training high-dimensional systems to optimize task reward under constraints

    arXiv
    2610.12432
    Published
    Layer
    Training and data layer
    Setting
    Embodied systems and robotics
    AbstractFAITH separates safety filtering from reward optimization.

    FAITH is a model-free safe filtering reinforcement learning framework for high-dimensional systems: safety correction and task reward reside in separate modules.

    Paper analysisRead analysis
  10. Analysis and theoryarXiv 2610.09517

    审计发现 CLIP 安全分数主要反映画面与提示词场景的相似度

    开环审计冻结视觉语言安全分，发现其反映场景模板而非危险感知

    arXiv
    2610.09517
    Published
    Layer
    Model layer
    Setting
    Embodied systems and robotics
    Evaluated models
    CLIP ViT-B/32, CLIP ViT-L/14, Qwen2-VL-7B
    Abstract论文审计了冻结 VLM 安全评分机制，指出其反映场景模板而非危险感知，为安全强化学习评估提供了严谨基准。

    本文是一项针对安全强化学习中冻结视觉语言模型（VLM）安全评分机制的实证审计研究。

    Paper analysisRead analysis
  11. DefensesarXiv 2610.09496

    SOUL：用稀疏特征策略遗忘缓解 VLA 模型的状态幻觉

    提出 SOUL 稀疏特征策略遗忘，缓解 VLA 状态幻觉

    arXiv
    2610.09496
    Published
    Layer
    Training and data layer
    Setting
    Embodied systems and robotics
    Evaluated models
    OpenVLA, π0.5
    AbstractSOUL 以稀疏特征遗忘 VLA 状态幻觉。

    SOUL用稀疏特征引导的策略 unlearning 处理 VLA 的 state hallucination。

    Paper analysisRead analysis
  14. OtherarXiv 2610.08917

    CARE：为视觉-语言-动作模型推理加速提供认证式选择

    提出 CARE，离线认证 VLA 加速配置的回合级失败风险并选出最快合格候选

    arXiv
    2610.08917
    Published
    Layer
    Model layer
    Setting
    Embodied systems and robotics
    Evaluated models
    OpenVLA-OFT, π0.5, π0 and others5
    AbstractCARE 以配对回合认证加速诱发失败，在预算内选最快候选，不足则保留参考。

    CARE 在部署前从加速配置中选出最快、且加速诱发失败风险能被有限样本认证为低于用户预算的候选。证据不足就保留全计算参考策略。

    Paper analysisRead analysis
  15. 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
  16. 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
  18. Evaluation and benchmarksarXiv 2610.06748

    BazaarBench：评估 LLM Agent 在去中心化 C2C 市场中的代理安全

    构建 BazaarBench，评测 C2C 市场中 Agent 的违规与失信行为

    arXiv
    2610.06748
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    GPT-5.5, GPT-5.4, GPT-5.4-mini and others5
    Abstract论文提出挂钩底层资产的 C2C 交易评测基准，发现时间压力与对抗指令显著推高了智能体的违规承诺与欺诈行为。

    BazaarBench 针对大语言模型智能体在去中心化 C2C 交易中的代理安全问题，提出了一个结合底层实体状态与大模型裁判的仿真基准平台。

    Paper analysisRead analysis
Load more