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

Oct 12 · Monday

All papers

Found 28 papers

Filter3

Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 265papers have no tags yet and are not included in filtered results.

Attack type：Prompt injection Impact：Unauthorized actions Attack surface / entry point：User input Clear all

Another 265papers do not have category tags yet and are not included in filtered results.

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
DefensesarXiv 2610.04504Oct 3
论文提出 VAL 框架：相同 ASR 的 LLM Agent 防御可能对应不同安全保证
提出 VAL 框架，并用确认门与参数沙箱约束智能体高风险工具调用
arXiv
2610.04504
Published
Oct 3
Layer
Application layer
Setting
AI Agent
Evaluated models
DeepSeek-chat, Meta Llama 3.1 8B, Kimi
- DefensesPermissions and approval
- AttacksPrompt injection
- ComponentPermissions and sandboxing
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.04378Oct 3
COPEX：面向 MCP 智能体的受控攻击评测基准发布
提出 COPEX 基准，评测 MCP 智能体对多入口攻击的抵抗力
arXiv
2610.04378
Published
Oct 3
Layer
Application layer
Setting
AI Agent
Evaluated models
Claude Opus 4.7, Claude Sonnet 4.6, GPT-5.5 and others9
- AttacksPrompt injection
- ComponentMCP and skills
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 2609.36603Sep 29
SED：面向 LLM 智能体的免训练持续安全策略学习框架
提出免训练框架 SED，将有害智能体轨迹蒸馏为可检索安全策略
arXiv
2609.36603
Published
Sep 29
Layer
Application layer
Setting
AI Agent
Evaluated models
DeepSeek-V4-Flash, GLM-5.2, Kimi K3
- DefensesInstruction–data separation
- AttacksPrompt injection
- ComponentMemory
Paper analysisRead analysis
AttacksarXiv 2609.33910Sep 28
论文提出残留授权重放攻击：长期运行 Agent 的授权可跨任务复用
提出残余权限重放攻击，跨任务复用长期 Agent 的历史授权绕过确认
arXiv
2609.33910
Published
Sep 28
Layer
Application layer
Setting
coding agent
Evaluated models
GPT-4.1, Gemini-3.1-Flash-Lite, Qwen3-14B and others6
- AttacksPrompt injection
- TechniqueDefense-targeted
- ComponentPermissions and sandboxing
Paper analysisRead analysis
DefensesarXiv 2609.33039Sep 27
TACIT：从 LLM 内部状态检测 Agent 轨迹危害
提出 TACIT，从冻结内部状态检测智能体有害轨迹
arXiv
2609.33039
Published
Sep 27
Layer
Application layer
Setting
AI Agent
Evaluated models
Qwen3-4B, Llama-3.1-8B, Qwen3-4B-Instruct and others4
- DefensesDetection and filtering
- AttacksPrompt injection
- ComponentGuardrails and judges
Abstract提出基于内部表征的智能体轨迹安全检测方法 TACIT，揭示工具风险表征特性并在多项基准上提升检测表现与效率。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.32616Sep 26
Cave-Bench：虚假指控下 LLM 智能体最高 60.06% 的运行会破坏正确工作
提出 CAVE-BENCH，评测智能体在虚假指责下破坏已完成的正确工作
arXiv
2609.32616
Published
Sep 26
Layer
Application layer
Setting
coding agent
Evaluated models
Claude-Sonnet-5, Claude-Opus-5, GPT-5.6-Sol and others14
- AttacksPrompt injection
- RiskDangerous agent actions
Abstract论文提出了评估智能体在虚假指责下破坏已有正确成果的 CAVE-BENCH，发现强模型易推翻已知证据，提出了门控缓解方案。
Paper analysisRead analysis
AttacksarXiv 2609.31318Sep 25
AgentXploit：面向 AI Agent 的仓库到运行时自动化红队系统
提出 AgentXploit，从代码仓库发现攻击路径并在运行时验证利用
arXiv
2609.31318
Published
Sep 25
Layer
Application layer
Setting
AI Agent
Evaluated models
GPT-4.1
- AttacksPrompt injection
Paper analysisRead analysis
DefensesarXiv 2609.24165Sep 21
APEXA 为同步辐射数据处理的 LLM 多智能体加装执行完整性护栏
提出 APEXA，在工具层拒绝无执行支撑的结果并拦截电机命令
arXiv
2609.24165
Published
Sep 21
Layer
Application layer
Setting
science agent
Evaluated models
GPT-5-mini, GPT-5.4, Claude Opus 4.7 and others4
- DefensesPermissions and approval
- AttacksPrompt injection
- RiskHallucination and fabrication
- ComponentPermissions and sandboxing
Abstract作者称执行是否发生要由工具层核对，而不能只靠提示词。
APEXA 是先进光子源上的数据还原框架，用工具层代码约束语言模型智能体的工具调用。
Paper analysisRead analysis
DefensesarXiv 2609.22573Sep 19
研究提出面向企业 MCP 的零信任授权与工具发现方案
提出企业 MCP 零信任授权与发现扩展，在架构上拒绝提示注入下的越权调用
arXiv
2609.22573
Published
Sep 19
Layer
Application layer
Setting
AI Agent
Evaluated models
gpt-5, claude-sonnet-4-6, claude-opus-4-7 and others6
- DefensesPermissions and approval
- AttacksPrompt injection
- ComponentMCP and skills
Abstract同一份按工具声明同时管 MCP 的发现、列表和调用，使注入不能扩大已有凭证的权限。
作者把零信任放在 MCP 工具调用边界：智能体即使被提示注入，也不能调用其凭证范围之外的工具。问题来自三点部署性质。调用意图会随不可信上下文改变。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.19705Sep 17
SoK 论文提出 FARSIGHT 框架，评测 15 个学术金融 LLM 交易 Agent 的鲁棒性与安全失败
用 FARSIGHT 方案级评测金融 LLM 交易 Agent 的稳健性与安全失败
arXiv
2609.19705
Published
Sep 17
Layer
Application layer
Setting
AI Agent
Evaluated models
ChatGPT Deep Research
- AttacksPrompt injection
- RiskDangerous agent actions
- ComponentMemory
Paper analysisRead analysis
DefensesarXiv 2609.16098Sep 14
研究者提出面向工具集成 LLM Agent 的通用对抗攻击防御方法
提出 ATF 与 NTR，过滤或恢复工具集以阻止 Agent 调用攻击工具
arXiv
2609.16098
Published
Sep 14
Layer
Application layer
Setting
AI Agent
Evaluated models
Gemma2-9B, Qwen2-7B, LLaMA3-8B and others7
- DefensesPermissions and approval
- AttacksPrompt injection
Paper analysisRead analysis
DefensesarXiv 2609.05903Sep 5
EvoSafeHarness：为 Agent 自动演化模型与领域专属安全护栏
为冻结模型与目标域自动搜索可部署的 Agent 安全 harness
arXiv
2609.05903
Published
Sep 5
Layer
Application layer
Setting
AI Agent
Evaluated models
Sonnet 4.6, GLM-5, Kimi-K2.5 and others11
- DefensesInstruction–data separation
- AttacksPrompt injection
- ComponentPermissions and sandboxing
Paper analysisRead analysis
DefensesarXiv 2609.02786Sep 3
SafeEvolve：基于智能体经验的 Harness-Policy 协同演化安全对齐框架
提出 SafeEvolve，用轨迹证据协同演化安全 harness 与策略
arXiv
2609.02786
Published
Sep 3
Layer
Application layer
Setting
AI Agent
Evaluated models
Qwen3.5-4B, Qwen3-4B-Instruct-2507, Qwen3.5-1.7B and others4
- DefensesModel hardening
- AttacksPrompt injection
AbstractSafeEvolve 用轨迹证据协同更新安全 harness 和策略，在两个 4B 模型的智能体安全基准上改变安全与效用。
SafeEvolve 把已完成的 on-policy 轨迹变成安全 harness 的有界更新，并用两阶段 SFT-RL 把这些更新内化进工具使用策略。
Paper analysisRead analysis
AttacksarXiv 2608.30441Aug 31
ECLIPSE：针对长程 Agent 系统的自演化隐蔽提示注入攻击
提出 ECLIPSE 双通道提示注入，劫持长程 Agent 的动作轨迹
arXiv
2608.30441
Published
Aug 31
Layer
Application layer
Setting
AI Agent
Evaluated models
DeepSeek, GPT-4o, Claude 4.8 Opus and others7
- AttacksPrompt injection
- TechniqueAutomated search
- ComponentMCP and skills
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 2608.17220Aug 18
PACE：为 DeFi 中的 AI Agent 提供策略认证的合约执行框架
提出 PACE，用策略认证与签名决策记录拦截 DeFi 智能体违规交易
arXiv
2608.17220
Published
Aug 18
Layer
Application layer
Setting
AI Agent
Evaluated models
gemini-3.1-flash-lite, DeepSeek-V4-Flash, gpt-4o
- DefensesPermissions and approval
- AttacksPrompt injection
- ComponentPermissions and sandboxing
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 2607.19913Jul 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

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

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 VAL 框架：相同 ASR 的 LLM Agent 防御可能对应不同安全保证

COPEX：面向 MCP 智能体的受控攻击评测基准发布

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

SED：面向 LLM 智能体的免训练持续安全策略学习框架

论文提出残留授权重放攻击：长期运行 Agent 的授权可跨任务复用

TACIT：从 LLM 内部状态检测 Agent 轨迹危害

Cave-Bench：虚假指控下 LLM 智能体最高 60.06% 的运行会破坏正确工作

AgentXploit：面向 AI Agent 的仓库到运行时自动化红队系统

APEXA 为同步辐射数据处理的 LLM 多智能体加装执行完整性护栏

研究提出面向企业 MCP 的零信任授权与工具发现方案

SoK 论文提出 FARSIGHT 框架，评测 15 个学术金融 LLM 交易 Agent 的鲁棒性与安全失败

研究者提出面向工具集成 LLM Agent 的通用对抗攻击防御方法

EvoSafeHarness：为 Agent 自动演化模型与领域专属安全护栏

SafeEvolve：基于智能体经验的 Harness-Policy 协同演化安全对齐框架

ECLIPSE：针对长程 Agent 系统的自演化隐蔽提示注入攻击

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

PACE：为 DeFi 中的 AI Agent 提供策略认证的合约执行框架

S³：用多阶段防御提升 LLM 智能体安全

Janus：面向长时程智能体安全的前瞻性潜在风险预测框架