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

Oct 13 · Tuesday

All papers

Found 167 papers

Filter6

System component

MCP and skills84 Memory83 RAG54 Guardrails and judges112 Monitors88 Reasoning chains63 Permissions and sandboxing92 Fine-tuning and open weights64 Vision81 Audio27 Video7 Image generation31 Embeddings13 Multimodal137

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：Model layer Layer：Application layer Layer：Training and data layer System component：Reasoning chains System component：Permissions and sandboxing System component：Embeddings 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
InterpretabilityarXiv 2610.12361Oct 9
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
Oct 9
Layer
Model layer
Setting
Models and APIs
Evaluated models
Qwen3-8B, Qwen3-14B, Llama-3.1-8B and others7
- AttacksPrompt injection
- ComponentReasoning chains
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
Analysis and theoryarXiv 2610.11765Oct 8
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
Oct 8
Layer
Model layer
Setting
Models and APIs
Evaluated models
Qwen3-4B, Qwen3-32B, Qwen3-235B-A22B and others6
- ComponentReasoning chains
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
DefensesarXiv 2610.11754Oct 8
仅凭输出审查无法验证什么：面向研究智能体的研究契约
提出研究合同，把已批准选择绑定到执行证据并由检查器核验
arXiv
2610.11754
Published
Oct 8
Layer
Application layer
Setting
science agent
Evaluated models
OpenAI gpt-5.6-sol, OpenAI gpt-5.6-terra, OpenAI gpt-5.6-luna and others18
- DefensesPermissions and approval
- RiskReward hacking
- ComponentPermissions and sandboxing
Abstract研究合同暴露四类输出单独建不立的关系。
研究合同用来核验计算科学研究智能体是否仍在已批准研究之内，不判断科学是否为真。。
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
Analysis and theoryarXiv 2610.10405Oct 8
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
Oct 8
Layer
Model layer
Setting
Models and APIs
Evaluated models
Gemma-4-e4b, Qwen-3.5-9b, GPT-OSS-120B
- RiskDeception and scheming
- ComponentReasoning chains
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
AttacksarXiv 2610.09920Oct 7
研究：多向量视觉文档索引可被反演还原页面内容
提出流匹配逆向框架，从多向量视觉文档索引重构页面
arXiv
2610.09920
Published
Oct 7
Layer
Application layer
Setting
LLM applications
Evaluated models
Tomoro-ColQwen3-8B, ColQwen3.5-4.5B, Tomoro-colqwen3-embed-4b and others13
- AttacksExtraction and theft
- ComponentEmbeddings
Paper analysisRead analysis
Analysis and theoryarXiv 2610.09667Oct 7
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
Oct 7
Layer
Model layer
Setting
Models and APIs
Evaluated models
GPT-6 Sol, GPT-6 Luna, GPT-5.4 mini and others6
- ComponentReasoning chains
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
InterpretabilityarXiv 2610.09087Oct 7
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
Oct 7
Layer
Model layer
Setting
Models and APIs
Evaluated models
Gemma-4-31B-it, Qwen3.5-27B, Magistral-Small-2507
- ComponentReasoning chains
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
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 2610.08082Oct 6
POLAR：面向小型工具调用智能体的可逆性护栏框架
提出 POLAR 本体门控，在执行前否决不可逆工具调用
arXiv
2610.08082
Published
Oct 6
Layer
Application layer
Setting
AI Agent
Evaluated models
qwen/qwen3-8b, meta-llama/llama-3.1-8b-instruct, nvidia/nemotron-nano-9b-v2 and others6
- DefensesPermissions and approval
- RiskDangerous agent actions
- ComponentPermissions and sandboxing
Abstract训练无关的事前可逆性门控，弱 airline 模型有收益，强模型与 retail 常回落。
POLAR 是训练无关的事前门控，用类型化本体在工具调用执行前检查能否组成候选逆序列。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.07639Oct 6
HarnessSecurity-Bench horizontally evaluates the security mechanisms of six coding agent frameworks.
评测编码智能体 harness 安全机制在对抗任务中的防护效果
arXiv
2610.07639
Published
Oct 6
Layer
Application layer
Setting
coding agent
- AttacksPrompt injection
- ComponentPermissions and sandboxing
Paper analysisRead analysis
OtherarXiv 2610.07459Oct 6
论文提出 AI Agent 声明的可审计性框架
提出 AI Agent 主张的可审计性框架与裁决规则
arXiv
2610.07459
Published
Oct 6
Layer
Application layer
Setting
AI Agent
- ComponentPermissions and sandboxing
Abstract主张须事先固定四要素。
作者给出把关于已部署智能体的主张写成可核查陈述的条件，而不是检测器或攻击方法。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.07359Oct 6
论文实测 Agent 工具调用门控栈的失败相关性
提出 nmult 并评测 Agent 动作门禁堆叠的错误相关性
arXiv
2610.07359
Published
Oct 6
Layer
Application layer
Setting
AI Agent
Evaluated models
AgentTrust runtime (174 rules), GPT-5.5 (gpt55), claude-haiku-4-5-20251001 and others7
- RiskDangerous agent actions
- ComponentPermissions and sandboxing
Abstract论文实测发现大模型裁判间错误显著相关，作者主张按机制选型并在整栈层面度量防护增益。
论文是一项针对智能体动作拦截防御堆叠故障关联性与实际组合价值的实证测量研究。
Paper analysisRead analysis
DefensesarXiv 2610.07258Oct 6
AMU：用派生血缘门控实现企业 AI Agent 列级访问控制
提出 AMU 按推导图门控企业 Agent 共享记忆的列级访问
arXiv
2610.07258
Published
Oct 6
Layer
Application layer
Setting
AI Agent
- DefensesPermissions and approval
- RiskDangerous agent actions
- ComponentMemory
Abstract在完整血缘下，AMU 按列权限放行缓存，并标出同名 KPI 冲突。
AMU 用列级推导门控共享记忆，拦截经缓存流出的无权敏感列，并标出同名 KPI 的定义冲突。
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 2610.06366Oct 5
VERA：结构化审计发现约 60% 正确漏洞判定伴随虚构推理
提出 VERA，审计 LLM 漏洞解释里的虚构推理
arXiv
2610.06366
Published
Oct 5
Layer
Model layer
Setting
coding agent
Evaluated models
sonnet-5, gemma-4-26b, llama-4-maverick and others8
- RiskHallucination and fabrication
- ComponentReasoning chains
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.05840Oct 5
研究：任务范围授权可将工具调用有害执行降至零
用配对回放评测任务范围授权能否阻断越权工具执行
arXiv
2610.05840
Published
Oct 5
Layer
Application layer
Setting
AI Agent
Evaluated models
Llama 3.2 3B Instruct Q4 K M, Qwen3 4B Instruct, Gemma 3 4B and others8
- DefensesPermissions and approval
- AttacksPrompt injection
- ComponentPermissions and sandboxing
Paper analysisRead analysis
DefensesarXiv 2610.05246Oct 4
研究测量策略网关跨平台命令裁决的能力边界
提出策略门裁决已实现动作，并测量跨平台命令拦截边界
arXiv
2610.05246
Published
Oct 4
Layer
Application layer
Setting
coding agent
Evaluated models
claude-opus-5, deepseek-v4.1-flash, gpt-6-astra
- DefensesPermissions and approval
- RiskDangerous agent actions
- ComponentPermissions and sandboxing
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

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

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

仅凭输出审查无法验证什么：面向研究智能体的研究契约

RL-ARC：用推理引导的不确定性校准大型推理模型

研究发现大语言模型被要求不诚实作答时推理 token 数上升

研究：多向量视觉文档索引可被反演还原页面内容

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

U-Space：揭示语言模型不确定性何时与为何产生

VeriFine：通过扩展验证实现具身推理的自我改进

POLAR：面向小型工具调用智能体的可逆性护栏框架

HarnessSecurity-Bench horizontally evaluates the security mechanisms of six coding agent frameworks.

论文提出 AI Agent 声明的可审计性框架

论文实测 Agent 工具调用门控栈的失败相关性

AMU：用派生血缘门控实现企业 AI Agent 列级访问控制

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

VERA：结构化审计发现约 60% 正确漏洞判定伴随虚构推理

研究：任务范围授权可将工具调用有害执行降至零

研究测量策略网关跨平台命令裁决的能力边界