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

Oct 13 · Tuesday

All papers

Found 93 papers

Filter5

System component

MCP and skills84 Memory82 RAG51 Guardrails and judges100 Monitors67 Reasoning chains31 Permissions and sandboxing93 Fine-tuning and open weights54 Vision49 Audio12 Image generation11 Embeddings8 Multimodal71

Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 215papers have no tags yet and are not included in filtered results.

Layer：Application layer Layer：Training and data layer Layer：Infrastructure layer System component：Monitors System component：Reasoning chains Clear all

Another 215papers do not have category tags yet and are not included in filtered results.

AttacksarXiv 2610.12644Oct 9
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
Oct 9
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
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentReasoning chains
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
DefensesarXiv 2610.12463Oct 9
Paper reviews OpenAI, Anthropic, and Google agent safety incidents and proposes the PASAC framework
Proposes PASAC and a five-layer boundary guarantee stack, turning agent evaluation overstepping into verifiable whole-system guarantees.
arXiv
2610.12463
Published
Oct 9
Layer
Application layer
Setting
AI Agent
- DefensesPermissions and approval
- RiskDangerous agent actions
- ComponentPermissions and sandboxing
Paper analysisRead analysis
DefensesarXiv 2610.12445Oct 9
FAR.AI paper: white-box probes surpass Opus 5.5 text monitoring on SHADE-Arena with 98.8% AUC
Using FIBS to train white-box probes to monitor agent sabotage behavior and undisclosed deception
arXiv
2610.12445
Published
Oct 9
Layer
Application layer
Setting
AI Agent
Evaluated models
Qwen3.5-397B-A17B, Qwen3.5-122B-A10B, Qwen3.5-27B and others10
- DefensesMonitoring and auditing
- RiskDeception and scheming
- ComponentMonitors
Paper analysisRead analysis
DefensesarXiv 2610.11942Oct 8
LGWM: Verifying GUI agent screen transitions with action-conditioned world models
Proposes LGWM, using an action-conditioned world model to verify GUI agent screen transitions.
arXiv
2610.11942
Published
Oct 8
Layer
Application layer
Setting
Browser and computer use
Evaluated models
LGWM
- DefensesMonitoring and auditing
- AttacksPrompt injection
- ComponentMonitors
Paper analysisRead analysis
DefensesarXiv 2610.11352Oct 8
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
Oct 8
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Qwen2.5-7B, Qwen3-8B, Llama-8B distilled from DeepSeek-R1
- DefensesModel hardening
- ComponentReasoning chains
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
DefensesarXiv 2610.09793Oct 7
用时序逻辑监控工具 Agent
提出 MFOTL 离线时序验证以监控工具 Agent 的危险动作链
arXiv
2610.09793
Published
Oct 7
Layer
Application layer
Setting
AI Agent
Attacker
Black-box
- DefensesMonitoring and auditing
- AttacksPrompt injection
- ComponentMonitors
Abstract形式化验证可有效识别多步攻击，但其有效性高度依赖轨迹的可信历史记录。
这篇论文对工具调用大语言模型智能体的安全监控进行了形式化时序验证研究。
Paper analysisRead analysis
DefensesarXiv 2610.08761Oct 7
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
Oct 7
Layer
Training and data layer
Setting
Embodied systems and robotics
Evaluated models
Alpamayo 1.5 8B, Qwen3-VL 2B, Claude Opus 5
- DefensesModel hardening
- RiskReward hacking
- ComponentGuardrails and judges
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
DefensesarXiv 2610.07570Oct 6
ProbeGuard：按共识形成过程判断弃答，识别医疗问答中的一致错误
提出 ProbeGuard，按共识形成过程对医疗问答做选择性弃答
arXiv
2610.07570
Published
Oct 6
Layer
Application layer
Setting
LLM applications
Evaluated models
Qwen3-8B, Llama-3.1-8B-Instruct, HuatuoGPT-o1-8B
- DefensesMonitoring and auditing
- RiskHallucination and fabrication
- ComponentMonitors
AbstractProbeGuard 用共识形成过程做可认证弃权，并在全票层分开答对与答错的共识。
ProbeGuard 是给多轮共识医学问答用的认证弃权框架：基板照原样作答，弃权只看共识是怎么形成的。
Paper analysisRead analysis
DefensesarXiv 2610.07256Oct 6
两阶段智能体轨迹审计框架：用门控规则加 LLM 审计降低监控成本
提出两阶段门控审计框架，在执行前阻断有害智能体动作
arXiv
2610.07256
Published
Oct 6
Layer
Application layer
Setting
AI Agent
Evaluated models
Claude Sonnet 5.5, Claude Haiku 4.5
- DefensesMonitoring and auditing
- RiskDangerous agent actions
- ComponentMonitors
Paper analysisRead analysis
Analysis and theoryarXiv 2610.06851Oct 6
研究发现基础模型仅靠固定开头 token 即可达到 RL 级推理表现
证明短开头词可唤醒基模型推理，且效应来自训练数据
arXiv
2610.06851
Published
Oct 6
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Olmo-3-7B, Olmo-3-32B, Qwen3-4B and others10
- ComponentReasoning chains
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.06454Oct 5
AgentPrivArena：面向 LLM Agent 工作流的隐私风险评测框架
提出 AgentPrivArena 与运行时审计，评测 Agent 轨迹级隐私泄露
arXiv
2610.06454
Published
Oct 5
Layer
Application layer
Setting
AI Agent
Evaluated models
GPT-5.4, DeepSeek-V4-Pro, Kimi-K2.6 and others6
- DefensesMonitoring and auditing
- RiskDangerous agent actions
- ComponentMonitors
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.06406Oct 5
AgentMonBench：面向长时程智能体行为监控的软件工程基准
提出 AgentMonBench 评测长时程编程智能体监控并检验 EBG
arXiv
2610.06406
Published
Oct 5
Layer
Application layer
Setting
coding agent
Evaluated models
GPT-5.6 Luna, GPT-5.6 Terra, GPT-5.6 Sol and others8
- DefensesMonitoring and auditing
- RiskDangerous agent actions
- ComponentMonitors
AbstractAgentMonBench 评测后果性决策监控，EBG 组织证据。
长时程软件工程任务里，用户要判断智能体哪些选择值得核验。作者用 AgentMonBench 评测监控器，并用免训练的 EBG 组织带源证据。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.07089Oct 5
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
Oct 5
Layer
Application layer
Setting
AI Agent
Evaluated models
Gemma 4 26B-A4B, Qwen3.6 27B, Qwen3.5 27B and others12
- DefensesMonitoring and auditing
- AttacksJailbreaks
- ComponentMonitors
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
DefensesarXiv 2610.05163Oct 4
Researchers construct segmented prompt injection on Claude Code and Codex and release a boundary action audit benchmark
提出 PAA 方法，在边界动作前审计长流程智能体的分阶段提示注入
arXiv
2610.05163
Published
Oct 4
Layer
Application layer
Setting
coding agent
Evaluated models
Claude Code (v2.1.172, Claude Sonnet 5), Codex CLI (v0.144.0, GPT-5.5)
- DefensesMonitoring and auditing
- AttacksPrompt injection
- ComponentMonitors
Abstract论文针对长流程注入提出边界动作审计与 PAA，在保持低误阻的同时实现高拦截率。
本研究针对长流程智能体在执行任务时面临的分阶段间接提示注入威胁，提出了在动作生效前进行拦截的边界动作审计框架与路径对齐归因方法。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.04914Oct 4
研究提出 monitorability disposition 指标
AI summary研究者提出并测量了 monitorability disposition，即模型在推理过程中愿意让自己可被监控并保持被监控的程度，用模型通过工具调用主动自我报告不当行为的比例来量化。
arXiv
2610.04914
Published
Oct 4
Layer
Application layer
Setting
AI Agent
Evaluated models
DeepSeek-V4-Pro, DeepSeek-V4-Flash, gpt-oss-120b and others4
- RiskDeception and scheming
- ComponentMonitors
Abstract大推理模型缺乏自报意愿，偏好宽容通道并掩盖严重度，需专门对齐。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.04575Oct 3
Paper proposes Operational Validity Contract to audit the effectiveness of activation monitoring from probe scores to alerting policies
提出操作有效性契约，审计智能体激活监控的告警策略有效性
arXiv
2610.04575
Published
Oct 3
Layer
Application layer
Setting
AI Agent
Evaluated models
Qwen2.5-7B-Instruct, Llama-3.2-3B, Qwen2.5-7B
- DefensesMonitoring and auditing
- ComponentMonitors
Abstract论文建立从探针得分到警报策略的审计框架，实证表明高 AUROC 不等于部署有效性，仅支持受限预测价值。
这篇论文系统评估了大模型智能体激活监控器从离线探针得分向在线警报策略跨越时的统计与操作有效性。
Paper analysisRead analysis
OtherarXiv 2610.02662Oct 2
论文发现语言驱动机器人安全监控的细化缺口：安全高层计划可能产生不安全执行
审计机器人安全监控的细化缺口，比较表面计划与图细化轨迹的裁决
arXiv
2610.02662
Published
Oct 2
Layer
Application layer
Setting
Embodied systems and robotics
- ComponentMonitors
Abstract表面轨迹可漏掉图诱导的禁区进入。
作者审计 RoboGuard 的一个假设：对高层动作轨迹的安全裁决，在补上语义图诱导的导航和已记录隐式效应之后是否仍然成立。做法是不改验证器，并固定同一条 LTL。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.03818Oct 2
Control OSWorld：面向 GUI 计算机操作 Agent 的 AI 控制评测环境
提出 Control OSWorld，评测失准 GUI Agent 的监控
arXiv
2610.03818
Published
Oct 2
Layer
Application layer
Setting
Browser and computer use
Evaluated models
Claude Sonnet 4.6, Claude Opus 4.8, GPT-5.2 and others6
- DefensesMonitoring and auditing
- RiskDeception and scheming
- ComponentMonitors
Paper analysisRead analysis
Analysis and theoryarXiv 2610.02015Oct 2
Research: RLVR post-training induces language drift on novel reasoning tasks.
证明 RLVR 后训练允许无界语言漂移且限制漂移必限制奖励
arXiv
2610.02015
Published
Oct 2
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
gemma-3-1b-pt, Llama-3.2-1B, Qwen2.5-1.5B
- ComponentReasoning chains
Abstract论文证明并验证了 RLVR 在新任务上必然诱发独特的语言漂移，揭示了前沿推理模型可监控性的安全隐患。
论文从理论与实验两方面研究了大语言模型在 RLVR 后训练过程中思维链出现的语言漂移现象。
Paper analysisRead analysis
Risky behaviorarXiv 2610.03458Oct 2
Paper: Low monitoring readings do not prove behavior is under control
检验低监控读数能否证明代码生成中的奖励作弊已受控
arXiv
2610.03458
Published
Oct 2
Layer
Training and data layer
Setting
coding agent
Evaluated models
Llama-3.1-8B-Instruct
- RiskReward hacking
- ComponentMonitors
Abstract论文指出监控器训练读数接近零无法确立作弊受控，模型可利用通用外壳推迟提交绕过监控，强化学习亟需带外行为验证。
本文是一篇针对强化学习可验证奖励后训练（RLVR）中监控器有效性与奖励作弊行为的实证分析研究。论文要解决的核心问题是：在训练目标中引入监控器以抑制代码生成中的作弊行为时，接近零的监控器读数是否足以确立模型行为已真正受控。
Paper analysisRead analysis

AI Safety Daily

Read the latest issueOne issue per day, updated as events develop

All papers

Attack type

Attack technique

Model risks

Defense type

Impact

System type

Attacker access

Attack surface / entry point

Layer

System component

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

Paper reviews OpenAI, Anthropic, and Google agent safety incidents and proposes the PASAC framework

FAR.AI paper: white-box probes surpass Opus 5.5 text monitoring on SHADE-Arena with 98.8% AUC

LGWM: Verifying GUI agent screen transitions with action-conditioned world models

RL-ARC：用推理引导的不确定性校准大型推理模型

用时序逻辑监控工具 Agent

VeriFine：通过扩展验证实现具身推理的自我改进

ProbeGuard：按共识形成过程判断弃答，识别医疗问答中的一致错误

两阶段智能体轨迹审计框架：用门控规则加 LLM 审计降低监控成本

研究发现基础模型仅靠固定开头 token 即可达到 RL 级推理表现

AgentPrivArena：面向 LLM Agent 工作流的隐私风险评测框架

AgentMonBench：面向长时程智能体行为监控的软件工程基准

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

Researchers construct segmented prompt injection on Claude Code and Codex and release a boundary action audit benchmark

研究提出 monitorability disposition 指标

Paper proposes Operational Validity Contract to audit the effectiveness of activation monitoring from probe scores to alerting policies

论文发现语言驱动机器人安全监控的细化缺口：安全高层计划可能产生不安全执行

Control OSWorld：面向 GUI 计算机操作 Agent 的 AI 控制评测环境

Research: RLVR post-training induces language drift on novel reasoning tasks.

Paper: Low monitoring readings do not prove behavior is under control