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

Oct 12 · Monday

All papers

Found 102 papers

Filter4

System component

MCP and skills82 Memory74 RAG46 Guardrails and judges95 Monitors66 Reasoning chains28 Permissions and sandboxing92 Fine-tuning and open weights50 Vision46 Audio12 Image generation11 Embeddings7 Multimodal68

Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 261papers have no tags yet and are not included in filtered results.

Layer：Application layer Layer：Training and data layer System component：Guardrails and judges System component：Embeddings Clear all

Another 261papers do not have category tags yet and are not included in filtered results.

AttacksarXiv 2610.12292Oct 9
The paper proposes an option channel attack: changing one option label can make an agent guardrail allow a prohibited operation
Proposing an option channel attack that renames option labels so that agent guardrails allow prohibited operations
arXiv
2610.12292
Published
Oct 9
Layer
Application layer
Setting
LLM applications
Attacker
Black-box
Evaluated models
LAYA-TD, LAYA-EN, LAYA-ML and others5
- AttacksDetection evasion
- ComponentGuardrails and judges
AbstractThe authors' evaluation indicates that typed models should not serve as final safety arbiters; they are susceptible to off-policy text and option name manipulation, and confidence filtering cannot resist attacks.
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.11773Oct 8
研究提出 Agent 安全新维度：识别未履行的安全义务
提出义务识别基准 ObligationBench，并训练护栏识别 Agent 未履行的安全义务
arXiv
2610.11773
Published
Oct 8
Layer
Application layer
Setting
coding agent
Evaluated models
ObligationGuard, Claude-Opus-4.8, GPT-5.6-Sol and others17
- DefensesDetection and filtering
- RiskDangerous agent actions
- ComponentGuardrails and judges
Abstract义务是护栏缺口。
作者认为编码智能体的安全不能只靠拦截禁止动作，还要找出终止时仍未做的安全关键动作，并将其称为义务。
Paper analysisRead analysis
DefensesarXiv 2610.11464Oct 8
研究者提出可检查评分器与自改进 Agent 共同演化方法
演化可检查评分器并与自改进 Agent 共同演化，抑制奖励作弊
arXiv
2610.11464
Published
Oct 8
Layer
Application layer
Setting
AI Agent
Evaluated models
Claude Opus 4.7
- DefensesDetection and filtering
- RiskReward hacking
- ComponentGuardrails and judges
Abstract十项锚点演化可检查评分器。
开放任务没有验证器时，被演化的是评分器，而不是再补一条手写 rubric。
Paper analysisRead analysis
DefensesarXiv 2610.11281Oct 8
包络采样：用少量真值标注重校准 LLM 评委以缓解奖励作弊
提出包络采样，用少量真值标注重标定 LLM 评委以缓解奖励作弊
arXiv
2610.11281
Published
Oct 8
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Qwen3-4B, Qwen3.8-27B, Qwen2.5-14B-Instruct
- DefensesModel hardening
- RiskReward hacking
- ComponentGuardrails and judges
Abstract包络采样把真值标注打到代理尾部，同样预算下缓解 reward hacking。
作者研究后训练前如何选择真值标注的查询分布，使重标定后的廉价代理更适合被优化。真奖励昂贵时，实践用 LLM judge 代替人类。若失准只发生在基座很少生成的输出上，on-policy 标注修不到这些点，随后的 KL 正则优化会把质量集中到被高估的输出。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.10947Oct 8
RH-Detect：统一的奖励作弊检测基准发布
构建统一奖励作弊检测基准 RH-Detect 并评测零样本检测器
arXiv
2610.10947
Published
Oct 8
Layer
Application layer
Setting
LLM applications
Evaluated models
Qwen 3.5 Flash, Gemini 3.1 Flash Lite, Grok 4.1 Fast and others7
- DefensesDetection and filtering
- RiskReward hacking
- ComponentGuardrails and judges
Paper analysisRead analysis
AttacksarXiv 2610.10742Oct 8
BRANCH 方法绕过 6 套多扫描器护栏系统
提出 BRANCH 方法，用分支搜索绕过多扫描器护栏
arXiv
2610.10742
Published
Oct 8
Layer
Application layer
Setting
LLM applications
Attacker
Black-box
Evaluated models
Meta Llama Guard 3 8B, Meta Llama Guard 7B, Meta Llama Guard 3 1B and others18
- AttacksDetection evasion
- TechniqueAutomated search
- ComponentGuardrails and judges
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
AttacksarXiv 2610.10612Oct 7
PyCache Trap 利用 Python 缓存替换绕过七款 Agent Skill 扫描器
提出 PyCache Trap，用字节码缓存替换绕过 Agent 技能扫描器
arXiv
2610.10612
Published
Oct 7
Layer
Application layer
Setting
coding agent
Evaluated models
CISCO, HSS, AUDITOR and others8
- DefensesDetection and filtering
- AttacksDetection evasion
- TechniqueDefense-targeted
- ComponentMCP and skills
Abstract论文剖析智能体技能审查与执行脱节盲区，提出 PyCache Trap 攻击并构建基于可信复现的 EAV 防御。
这篇论文研究了智能体技能（Agent Skills）安全扫描中的“审查–执行脱节”问题，并提出了对应的攻击验证与防御方案。
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
Evaluation and benchmarksarXiv 2610.08571Oct 6
RAG-PIBench：可信 RAG 系统中提示注入检测的泄漏感知基准
提出 RAG-PIBench，评测 RAG 上下文中提示注入检测器
arXiv
2610.08571
Published
Oct 6
Layer
Application layer
Setting
LLM applications
Evaluated models
DistilBERT-base-uncased, DeBERTa-v3-base, MiniLM
- DefensesDetection and filtering
- AttacksPrompt injection
- ComponentRAG
Paper analysisRead analysis
AttacksarXiv 2610.07723Oct 6
Researchers propose answer-side backdoors: letting the model self-generate trigger words to bypass safety refusals.
提出回答端后门，让模型自生成触发词以在干净有害请求下绕过拒答
arXiv
2610.07723
Published
Oct 6
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Llama-2-7B-chat-hf, Mistral-7B-Instruct-v0.3, Gemma-7B-it and others4
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentFine-tuning and open weights
Abstract论文提出了多轮对话中回答端自生成触发词绕过安全拒绝的后门攻击，指出输入端防护存在盲区。
Paper analysisRead analysis
DefensesarXiv 2610.07657Oct 6
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
Oct 6
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
- DefensesPermissions and approval
- AttacksPrompt injection
- ComponentGuardrails and judges
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
Evaluation and benchmarksarXiv 2610.07519Oct 6
论文提出针对手语翻译与儿童安全过滤交叉地带的部署前审计框架
提出手语转文本接入儿童安全过滤的部署前审计协议
arXiv
2610.07519
Published
Oct 6
Layer
Application layer
Setting
LLM applications
- DefensesDetection and filtering
- ComponentGuardrails and judges
Abstract作者提议聋人知情的部署前审计，以检查手语转文本是否改变儿童安全决策。
手语儿童到达基于文本的儿童安全机制时，机制看到的是机器翻译，不是儿童所做的手语。作者要解决的是：这条边界在部署前应如何审计。
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
AttacksarXiv 2610.05943Oct 5
CRIME 框架利用良性 Agent 技能组合诱发恶意行为
提出 CRIME 框架，组合良性 Agent 技能诱发恶意行为
arXiv
2610.05943
Published
Oct 5
Layer
Application layer
Setting
AI Agent
Evaluated models
DeepSeek-V4-Flash, GPT-4o-mini, GPT-4o and others6
- AttacksJailbreaks
- TechniqueAutomated search
- ComponentMCP and skills
Abstract良性技能经 DCA 或 ACA 组合后可产生恶意环境后果，单独审查对不上。
CRIME 把公共技能库中各自通过审查的技能配成两两组合，看联合执行能否实现指定恶意任务。。
Paper analysisRead analysis
DefensesarXiv 2610.05870Oct 5
MBZUAI 提出可校准的真实图像认证方法
提出校准重合成方法，以生成器反演保真度认证真实图像并防御对抗扰动
arXiv
2610.05870
Published
Oct 5
Layer
Application layer
Setting
LLM applications
Attacker
White-box
- DefensesDetection and filtering
- AttacksDetection evasion
- ComponentImage generation
Abstract论文提出基于反演保真度与阈值校准的健全认证框架，在对抗扰动下维持错误率界限，并指出真实内容可认证性随生成器演进而萎缩。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.05830Oct 5
研究提出智能体排行榜污染审计框架，并检验评分器有效性
提出 HAL 污染审计框架并核验智能体排行榜评分器
arXiv
2610.05830
Published
Oct 5
Layer
Application layer
Setting
AI Agent
Evaluated models
GPT-4.1, DeepSeek-V4-Flash
- ComponentGuardrails and judges
Abstract框架分开易感性与已实现事件。
作者给出一套测量优先审计框架，用来判断智能体排行榜上的污染主张各自需要何种证据。
Paper analysisRead analysis
DefensesarXiv 2610.05308Oct 4
RubricArmor：用对抗演化改进 LLM 评分标准生成
提出 RubricArmor，用攻击–修复循环生成抗奖励作弊的评分准则
arXiv
2610.05308
Published
Oct 4
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Qwen2.5-3B-Instruct, Qwen2.5-7B-Instruct, Qwen3-4B and others8
- RiskReward hacking
- ComponentGuardrails and judges
Paper analysisRead analysis
DefensesarXiv 2610.04412Oct 3
论文研究 LLM 数字孪生参与增强民主时的提示注入脆弱性
提出检测、结构化与 GSPO 流程，降低共识生成的提示注入错位
arXiv
2610.04412
Published
Oct 3
Layer
Application layer
Setting
LLM applications, Multi-agent systems
Evaluated models
LLaMA-2 7B, LLaMA-3 8B, GPT 3.5 Turbo and others14
- DefensesDetection and filtering
- AttacksPrompt injection
- ComponentGuardrails and judges
Abstract三章依次做个体偏好预测、政党知识图谱审议，以及共识生成对提示注入的脆弱性与一条防御流程。
这是一篇把 LLM 数字孪生放进增强民主的博士论文，分个体表示、政党聚合和共识生成的提示注入三章。
Paper analysisRead analysis
DefensesarXiv 2610.03434Oct 2
Persona Guardrail：面向智能体系统的生产级防御框架
提出 Persona Guardrail，强制客服智能体守住功能边界
arXiv
2610.03434
Published
Oct 2
Layer
Application layer
Setting
AI Agent
Attacker
Black-box
Evaluated models
Qwen3-30B-A3B, Qwen3-VL-30B, Qwen3-8B and others5
- DefensesDetection and filtering
- AttacksJailbreaks
- ComponentGuardrails and judges
AbstractPersona Guardrail 用功能边界做同步输入输出校验，并在 PAGE 与生产延迟预算下给出评测。
Persona Guardrail 是客服向智能体的同步运行时防御：先写明功能边界，再决定放行或拦截，而不是只检测某一攻击类。
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

The paper proposes an option channel attack: changing one option label can make an agent guardrail allow a prohibited operation

研究提出 Agent 安全新维度：识别未履行的安全义务

研究者提出可检查评分器与自改进 Agent 共同演化方法

包络采样：用少量真值标注重校准 LLM 评委以缓解奖励作弊

RH-Detect：统一的奖励作弊检测基准发布

BRANCH 方法绕过 6 套多扫描器护栏系统

研究：多向量视觉文档索引可被反演还原页面内容

PyCache Trap 利用 Python 缓存替换绕过七款 Agent Skill 扫描器

VeriFine：通过扩展验证实现具身推理的自我改进

RAG-PIBench：可信 RAG 系统中提示注入检测的泄漏感知基准

Researchers propose answer-side backdoors: letting the model self-generate trigger words to bypass safety refusals.

DEFER1 多智能体防御研究报告受控测试中的攻击成功率下降

论文提出针对手语翻译与儿童安全过滤交叉地带的部署前审计框架

论文实测 Agent 工具调用门控栈的失败相关性

CRIME 框架利用良性 Agent 技能组合诱发恶意行为

MBZUAI 提出可校准的真实图像认证方法

研究提出智能体排行榜污染审计框架，并检验评分器有效性

RubricArmor：用对抗演化改进 LLM 评分标准生成

论文研究 LLM 数字孪生参与增强民主时的提示注入脆弱性

Persona Guardrail：面向智能体系统的生产级防御框架