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

Oct 12 · Monday

All papers

Found 29 papers

Filter4

Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 255papers have no tags yet and are not included in filtered results.

Attack type：Prompt injection System component：Monitors System component：Reasoning chains System component：Embeddings Clear all

Another 255papers do not have category tags yet and are not included in filtered results.

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
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 2610.09793Oct 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
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
DefensesarXiv 2610.02413Oct 2
研究：分类后缀可提升激活探针的分布外恶意输入检测
用分类后缀提升激活探针对分布外恶意输入的检测
arXiv
2610.02413
Published
Oct 2
Layer
Model layer
Setting
Models and APIs
Evaluated models
Llama-3.1-8B, Qwen3.5-9B, Gemma-4-12B
- DefensesMonitoring and auditing
- AttacksJailbreaks
- ComponentMonitors
Abstract作者称排序增益来自分类格式，低 FPR 精度来自点名准则。
用户轮后的分类后缀，被作者用作激活探针的分布外检测干预：排序看格式，低 FPR 精度看是否点名恶意/良性。
Paper analysisRead analysis
DefensesarXiv 2610.00400Sep 30
DART: Detecting emerging safety risks in multi-turn LLM agents with representation shift
提出 DART，用去噪表征转移检测多轮智能体攻击并注入提醒
arXiv
2610.00400
Published
Sep 30
Layer
Application layer
Setting
AI Agent
Attacker
Black-box
Evaluated models
Qwen3-8B, Qwen3-14B, Qwen3-32B and others6
- DefensesMonitoring and auditing
- AttacksJailbreaks
- ComponentMonitors
Paper analysisRead analysis
DefensesarXiv 2609.35659Sep 29
Tracekit：面向自主编码 Agent 的防篡改意图-推理-动作审计系统
提出 Tracekit，审计编码 Agent 的意图、推理与动作并检测账本篡改
arXiv
2609.35659
Published
Sep 29
Layer
Application layer
Setting
coding agent
Evaluated models
Claude Code (claude -p, version 2.1), 独立评审（同一 CLI，无工具）
- DefensesMonitoring and auditing
- AttacksPrompt injection
- RiskDangerous agent actions
- ComponentMonitors
AbstractTracekit 把意图、自述和动作写入可锚定的哈希链。
Tracekit 是无第三方依赖的编码智能体审计层：把人类请求、模型自述和已执行动作并排写入可外部锚定的哈希链，执行前用正则门，事后用规则和独立模型互查。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.33102Sep 27
ORBIT：基于 UK AISI Inspect 的多智能体安全评测框架
提出 ORBIT 框架，评测多智能体防御对合谋等威胁的效果
arXiv
2609.33102
Published
Sep 27
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
GPT-5.4, Claude Sonnet 4.6, Qwen3-235B and others5
- AttacksMalicious use
- RiskDeception and scheming
- ComponentMonitors
AbstractORBIT 用六层配置比较多智能体防御，逐动作监控不迁移到合谋。
Paper analysisRead analysis
Risky behaviorarXiv 2609.30266Sep 25
研究显示 Claude Code、Codex 等本地智能体可轻易篡改自身执行轨迹
测试编程智能体被诱导或自主篡改自身执行轨迹的行为
arXiv
2609.30266
Published
Sep 25
Layer
Application layer
Setting
coding agent
Evaluated models
GPT-5.6-Sol, GPT-6-Sol, Opus-5 and others11
- AttacksMalicious use
- RiskDeception and scheming
- ComponentMonitors
Abstract论文评估了本地智能体的轨迹防篡改能力，发现其可因外部指令或奖励追求而清除执行证据，亟需建立独立拦截记录机制。
这是一项针对本地大模型智能体执行轨迹完整性与安全防篡改边界的实证研究。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.28915Sep 24
研究提出 ACE 语料库，评估内核级证据对 Agent 安全检测的有效性
构建 ACE 语料，评测内核级证据对 Agent 攻击检测的有效性
arXiv
2609.28915
Published
Sep 24
Layer
Application layer
Setting
coding agent
Evaluated models
AdaBoost, XGBoost, TabPFN and others10
- AttacksPrompt injection
- ComponentMCP and skills
AbstractACE 用配对的内核与应用层证据表明，syscall 痕迹可判别智能体攻击，两层组合通常更好。
ACE 是一份把智能体会话的内核 syscall 痕迹与应用层清单、转录配对起来的检测语料和基准。。
Paper analysisRead analysis
AttacksarXiv 2609.27542Sep 23
Researchers use control token injection to delete gpt-oss-20b's reasoning chain and bypass chain-of-thought monitoring
提出控制标记注入，清空工具 Agent 的思维链以绕过推理监控
arXiv
2609.27542
Published
Sep 23
Layer
Application layer
Setting
AI Agent
Evaluated models
openai/gpt-oss-20b, google/gemma-4-26B-A4B-it, deepseek-ai/DeepSeek-R1-Distill-Qwen-7B and others4
- AttacksPrompt injection
- TechniqueConversation structure manipulation
- ComponentReasoning chains
Abstract论文阐明控制标记注入可抑制 CoT 使监控失效并促成拒绝绕过，且工具执行受解析器宽容度影响。
Paper analysisRead analysis
AttacksarXiv 2609.01023Sep 1
Akrasia：针对推理型代码 LLM 的隐蔽后门攻击
提出隐蔽后门攻击 AKRASIA，在推理代码模型提示中植入触发器并伪装思维链
arXiv
2609.01023
Published
Sep 1
Layer
Prompt layer
Setting
coding agent
Evaluated models
Claude-Sonnet-5, GPT-5.5, Gemini-3.5-flash and others7
- AttacksPrompt injection
- TechniqueReasoning-chain manipulation
- ComponentReasoning chains
Abstract论文针对推理代码大模型提出了隐蔽推断期后门攻击 AKRASIA，揭示了模型思维链可被利用进行欺骗性伪装的安全隐患。
Paper analysisRead analysis
DefensesarXiv 2608.21101Aug 21
ClawSentry：面向自主 LLM Agent 的渐进式多层安全监控网关
提出 ClawSentry 多层监控网关，在技能准入和运行时拦截恶意技能与隐藏指令
arXiv
2608.21101
Published
Aug 21
Layer
Application layer
Setting
coding agent
Evaluated models
Codex/GPT-5.4, Codex/GPT-5.5, Claude Code/GLM-5.1 and others6
- DefensesMonitoring and auditing
- AttacksPoisoning and backdoors
- ComponentMCP and skills
AbstractClawSentry 用包准入、三级运行时门控和反绕过，压低 skill 攻击并保住干净任务。
ClawSentry 是挂在智能体运行时之外的安全监督网关，用来同时盖住 skill 执行的多个生命周期边界，并把已被拒绝的效果记到会话里。
Paper analysisRead analysis
DefensesarXiv 2608.02683Aug 3
S³：用多阶段防御提升 LLM 智能体安全
提出 S³，用 guard agent 编排阶段安全技能防御智能体多阶段风险
arXiv
2608.02683
Published
Aug 3
Layer
Application layer
Setting
Embodied systems and robotics
Evaluated models
DeepSeek-V4-Pro, DeepSeek-V4-Flash
- DefensesMonitoring and auditing
- AttacksPoisoning and backdoors
- RiskDangerous agent actions
- ComponentMonitors
Paper analysisRead analysis
DefensesarXiv 2607.25297Jul 28
MTGuard: Hybrid Analysis for Secure MCP Tool Calls in LLM Agents
Proposes MTGuard, which blocks unsafe tool calls by comparing MCP call declarations with execution traces.
arXiv
2607.25297
Published
Jul 28
Layer
Application layer
Setting
AI Agent
Evaluated models
DeepSeek-V4-Flash, DeepSeek-V4-Pro, GPT-5.6 Luna
- DefensesMonitoring and auditing
- AttacksPoisoning and backdoors
- ComponentMCP and skills
Paper analysisRead analysis
DefensesarXiv 2607.19913Jul 22
Janus：面向长时程智能体安全的前瞻性潜在风险预测框架
提出 Janus 前瞻守卫，在长程智能体执行有害动作前拦截潜在风险
arXiv
2607.19913
Published
Jul 22
Layer
Application layer
Setting
AI Agent
Evaluated models
Vanguard
- DefensesMonitoring and auditing
- AttacksPrompt injection
- RiskDangerous agent actions
- ComponentMonitors
Paper analysisRead analysis
AttacksarXiv 2607.00422Jul 1
KidnapRAG：黑盒投毒攻击劫持 Agentic RAG 的推理链
提出 KidnapRAG，用投毒文档黑盒劫持 Agentic RAG 的推理链
arXiv
2607.00422
Published
Jul 1
Layer
Application layer
Setting
AI Agent
Evaluated models
Qwen2.5-32B-Instruct, Llama-3.3-70B-Instruct, QwQ-32B and others5
- AttacksPoisoning and backdoors
- TechniqueSelection manipulation
- ComponentReasoning chains
Abstract顺序投毒可把多步推理拖向指定应答，作者称关键在持续引导而非单次注入。
KidnapRAG 是针对 Agentic RAG 的 black-box 语料投毒：攻击者不能访问模型、提示词、检索器或私有轨迹，只能发布可能被检索的文档，并利用公开界面上的推理与搜索查询。
Paper analysisRead analysis
DefensesarXiv 2606.22673Jun 22
Agent MechSuits：面向多轮 CLI Agent 的机制子空间安全引导
提出 Agent MechSuits，对多轮 CLI Agent 做步级检测与子空间转向
arXiv
2606.22673
Published
Jun 22
Layer
Application layer
Setting
coding agent
Evaluated models
LLaMA-3.1-8B, Qwen-2.5-7B, Gemma-2-9B
- DefensesInference-time intervention
- AttacksMalicious use
- ComponentMonitors
Abstract白盒步级探针加稀疏转向可压低三模型恶意动作，同时提高生成崩溃率。
Agent MechSuits 是面向多轮 CLI 智能体的白盒、步级表示防御，并配有可执行轨迹基准 MAS。
Paper analysisRead analysis
AttacksarXiv 2606.12716Jun 11
PaperGuard：针对多模态 AI 同行评审的攻击与防御基准
提出 PaperGuard，用图文注入与梯度扰动抬高自动审稿分数并检测恶意指令
arXiv
2606.12716
Published
Jun 11
Layer
Application layer
Setting
LLM applications
Evaluated models
Claude-sonnet-4.5, GPT-4o, GPT-4.1 and others11
- AttacksPrompt injection
- TechniqueCross-modal payloads
- ComponentVision
AbstractPaperGuard 测到提示注入与白盒视觉抬分，并比较分块检索防御。
PaperGuard同时评测并检测多模态 AI 审稿中的评分操纵。
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

Attack surface / entry point

Layer

System component

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

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

用时序逻辑监控工具 Agent

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：分类后缀可提升激活探针的分布外恶意输入检测

DART: Detecting emerging safety risks in multi-turn LLM agents with representation shift

Tracekit：面向自主编码 Agent 的防篡改意图-推理-动作审计系统

ORBIT：基于 UK AISI Inspect 的多智能体安全评测框架

研究显示 Claude Code、Codex 等本地智能体可轻易篡改自身执行轨迹

研究提出 ACE 语料库，评估内核级证据对 Agent 安全检测的有效性

Researchers use control token injection to delete gpt-oss-20b's reasoning chain and bypass chain-of-thought monitoring

Akrasia：针对推理型代码 LLM 的隐蔽后门攻击

ClawSentry：面向自主 LLM Agent 的渐进式多层安全监控网关

S³：用多阶段防御提升 LLM 智能体安全

MTGuard: Hybrid Analysis for Secure MCP Tool Calls in LLM Agents

Janus：面向长时程智能体安全的前瞻性潜在风险预测框架

KidnapRAG：黑盒投毒攻击劫持 Agentic RAG 的推理链

Agent MechSuits：面向多轮 CLI Agent 的机制子空间安全引导

PaperGuard：针对多模态 AI 同行评审的攻击与防御基准