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

Oct 12 · Monday

All papers

Found 19 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.

Defense type：Detection and filtering Attack surface / entry point：Tool responses Attack surface / entry point：Weights and gradients 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 2610.03073Oct 2
SecJev：为 System One 决策模型引入安全专业知识
提出 SecJev，用场景加权训练把决策模型适配为安全类型化判断
arXiv
2610.03073
Published
Oct 2
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
SecJev-0.8B, SecJev-2B, SecJev-4B and others4
- DefensesDetection and filtering
- AttacksPrompt injection
- ComponentGuardrails and judges
AbstractSecJev 用共享打分器做安全决策，0.8B 的 task-macro 超过 Kev-9B。
SecJev 是 0.8B 到 9B 的安全决策模型族，作者称据其所知是首个面向安全的 Jev-like 家族。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.03448Oct 2
研究重测 15 个提示注入检测器：基准分数难以预测 Agent 部署表现
重测提示注入检测器在 Agent 工具输出上的检出与任务阻断
arXiv
2610.03448
Published
Oct 2
Layer
Application layer
Setting
AI Agent
Evaluated models
Horizon-Labs, Wolf Defender, Prismor-1.5B and others15
- DefensesDetection and filtering
- AttacksPrompt injection
- ComponentGuardrails and judges
Abstract论文揭示公开基准无法反映智能体检测器表现，检测能力源于输入格式相似而非通用防御，建议基于工具输出与低误报评测。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.35886Sep 27
Agentic Commerce Bench：衡量会花钱的智能体的欺诈检测能力
构建支付欺诈基准 ACB，评测花钱智能体的欺诈检测
arXiv
2609.35886
Published
Sep 27
Layer
Application layer
Setting
AI Agent
Evaluated models
gordonguard, pattern judge
- DefensesDetection and filtering
- RiskDangerous agent actions
- ComponentGuardrails and judges
AbstractACB 把支付欺诈与智能体操纵分开测量，作者强调观察权限、误报预算和微支付复核成本。
ACB 是一套智能体支付欺诈基准与检测参考栈，目标是衡量钱是否被不当提取，而不仅是智能体是否接受了恶意指令。
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 2609.29429Sep 24
Jev 被用于零样本检测十类对齐失败，中位 AUROC 达 0.886
提出 RLCDAlignBench，零样本检测多种对齐失败
arXiv
2609.29429
Published
Sep 24
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
Jev (jev-1.13.0)
- DefensesDetection and filtering
- AttacksJailbreaks
- RiskMisalignment and value divergence
- ComponentGuardrails and judges
Abstract一次通用问题已能给多数对齐失败排序，大的误差来自状态和标签。
RLCDAlignBench 测量用强化学习做校准决策的 Jev，能否当作对齐失败的零样本检测器。
Paper analysisRead analysis
AttacksarXiv 2609.27124Sep 23
Fed-ADR：用恶意编排服务器协同客户端梯度操纵攻击联邦学习
提出 Fed-ADR，用编排服务器协同操纵梯度攻破联邦学习并检测恢复
arXiv
2609.27124
Published
Sep 23
Layer
Training and data layer
Setting
Models and APIs
Attacker
Gray-box
Evaluated models
CNN（MNIST：2 Conv + 3 FC）, CNN（Fashion-MNIST：6 Conv + 1 FC）, ResNet18（CIFAR-10）
- DefensesDetection and filtering
- AttacksPoisoning and backdoors
- TechniqueDefense-targeted
AbstractFed-ADR 用 gray-box 编排攻击绕过多种聚合防御，再用 Hessian 一致性检测和窗口内恢复把准确率拉回。
Fed-ADR 是一套面向联邦学习的攻击、检测与恢复框架：编排服务器改写合谋客户端的梯度，使参数服务器的现有防御把投毒更新当成良性，同时在发现后用历史梯度把全局模型原地修回来。
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 2609.14987Sep 14
ActGuard：面向 LLM Agent 间接提示注入的执行前动作审计框架
提出 ActGuard 执行前动作审计，定位并遮盖间接提示注入的恶意片段
arXiv
2609.14987
Published
Sep 14
Layer
Application layer
Setting
AI Agent
Evaluated models
GPT-4o-mini, Gemini-2.5-Flash, DeepSeek-V4-Flash
- DefensesMonitoring and auditing
- AttacksPrompt injection
Paper analysisRead analysis
DefensesarXiv 2609.10854Sep 10
MCPSEC：仅凭工具元数据检测 MCP 服务器间接提示注入漏洞
提出 MCPSEC，仅凭工具元数据无盒检测 MCP 间接提示注入漏洞
arXiv
2609.10854
Published
Sep 10
Layer
Application layer
Setting
AI Agent
- DefensesDetection and filtering
- AttacksPrompt injection
- ComponentMCP and skills
Paper analysisRead analysis
DefensesarXiv 2609.10707Sep 10
面向 AI-SOC 的神经符号防御框架：用 SIEM 解码器与 NeMo Guardrails 阻断日志投毒提示注入
提出神经符号纵深架构，阻断 AI-SOC 的日志投毒与间接提示注入
arXiv
2609.10707
Published
Sep 10
Layer
Application layer
Setting
LLM applications
Evaluated models
Gemma 3 (12B)
- DefensesDetection and filtering
- AttacksPrompt injection
- ComponentGuardrails and judges
Paper analysisRead analysis
DefensesarXiv 2609.27760Sep 4
FedMAST：用多轴结构痕迹检测并遏制联邦学习后门
提出 FedMAST，用多轴结构痕迹检测并遏制联邦学习后门
arXiv
2609.27760
Published
Sep 4
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Tiny ResNet-18
- DefensesDetection and filtering
- AttacksPoisoning and backdoors
Paper analysisRead analysis
DefensesarXiv 2609.02127Sep 2
论文提出带类型溯源与断言护栏，防止持久化 AI Agent 把不可信输入当作自身历史
提出类型化溯源与断言护栏，约束持久 Agent 释放自传断言
arXiv
2609.02127
Published
Sep 2
Layer
Application layer
Setting
AI Agent
- DefensesWatermarking and provenance
- AttacksPoisoning and backdoors
- ComponentMemory
Paper analysisRead analysis
DefensesarXiv 2608.02271Aug 3
Z-PEFT：基于规范谱特征的参数高效微调零样本后门检测
提出 Z-PEFT，用逐头谱特征零样本检测 PEFT 后门
arXiv
2608.02271
Published
Aug 3
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Z-PEFT, Llama-2-7B, Llama-2-13B and others6
- DefensesDetection and filtering
- AttacksPoisoning and backdoors
- ComponentFine-tuning and open weights
Paper analysisRead analysis
DefensesarXiv 2607.25297Jul 28
MTGuard：面向 LLM 智能体安全 MCP 工具调用的混合分析
提出 MTGuard，对照 MCP 调用声明与执行痕迹拦截不安全工具调用
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
AttacksarXiv 2607.06595Jul 7
当 Agent 记得太多：针对大语言模型 Agent 的记忆投毒攻击
提出 GhostWriter 记忆投毒，经邮件与日程写入 Agent 长期记忆并跨会话激活
arXiv
2607.06595
Published
Jul 7
Layer
Application layer
Setting
AI Agent
Evaluated models
GPT-5.4-mini, DeepSeek-V4-Flash, Gemini-2.5-Flash and others4
- DefensesDetection and filtering
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentMemory
Paper analysisRead analysis
DefensesarXiv 2603.14707Mar 16
视觉混淆代理：利用与防御计算机使用智能体的感知失效
提出进程外双通道对比分类，拦截计算机使用智能体的错误点击
arXiv
2603.14707
Published
Mar 16
Layer
Application layer
Setting
Browser and computer use
Evaluated models
multi-modal-embed-small
- DefensesDetection and filtering
- AttacksPrompt injection
- RiskDangerous agent actions
- ComponentGuardrails and judges
Abstract感知错误可被屏幕像素对调利用。
作者把 CUA 的感知失败写成安全漏洞visual confused deputy：智能体按看错的屏幕授权 click(x,y)，真实落点与它以为的元素不一致。
Paper analysisRead analysis
DefensesarXiv 2601.10156Jan 15
ToolSafe 提出步骤级护栏 TS-Guard 与 TS-Flow，降低 Agent 有害工具调用
提出 TS-Guard 与 TS-Flow，在执行前检测并引导 Agent 修正有害工具调用
arXiv
2601.10156
Published
Jan 15
Layer
Application layer
Setting
AI Agent
Evaluated models
GPT-4o, TS-Guard, Qwen2.5-14B-Instruct
- DefensesDetection and filtering
- AttacksJailbreaks
- ComponentGuardrails and judges
AbstractTS-Bench 标步骤级风险，TS-Guard 用多任务 RL 做执行前判定，TS-Flow 用反馈代替直接中止。
ToolSafe 研究 LLM 智能体在工具执行前的步骤级安全：基准 TS-Bench、护栏 TS-Guard，以及反馈驱动框架 TS-Flow。
Paper analysisRead analysis
DefensesarXiv 2511.20597Nov 26, 2025
BrowseSafe：研究者构建浏览器 Agent 提示注入基准并评测现有防御
提出 BrowseSafe，在工具输出边界检测并拦截浏览器 Agent 提示注入
arXiv
2511.20597
Published
Nov 26, 2025
Layer
Application layer
Setting
web agent
Evaluated models
Qwen3-30B-A3B-Instruct-2507, Qwen3-8B, PromptGuard-2 (22M) and others10
- DefensesDetection and filtering
- AttacksPrompt injection
- ComponentGuardrails and judges
Paper analysisRead analysis

You have reached the end

AI Safety Daily

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

All papers

Attack type

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

SecJev：为 System One 决策模型引入安全专业知识

研究重测 15 个提示注入检测器：基准分数难以预测 Agent 部署表现

Agentic Commerce Bench：衡量会花钱的智能体的欺诈检测能力

TACIT：从 LLM 内部状态检测 Agent 轨迹危害

Jev 被用于零样本检测十类对齐失败，中位 AUROC 达 0.886

Fed-ADR：用恶意编排服务器协同客户端梯度操纵攻击联邦学习

研究者提出面向工具集成 LLM Agent 的通用对抗攻击防御方法

ActGuard：面向 LLM Agent 间接提示注入的执行前动作审计框架

MCPSEC：仅凭工具元数据检测 MCP 服务器间接提示注入漏洞

面向 AI-SOC 的神经符号防御框架：用 SIEM 解码器与 NeMo Guardrails 阻断日志投毒提示注入

FedMAST：用多轴结构痕迹检测并遏制联邦学习后门

论文提出带类型溯源与断言护栏，防止持久化 AI Agent 把不可信输入当作自身历史

Z-PEFT：基于规范谱特征的参数高效微调零样本后门检测

MTGuard：面向 LLM 智能体安全 MCP 工具调用的混合分析

当 Agent 记得太多：针对大语言模型 Agent 的记忆投毒攻击

视觉混淆代理：利用与防御计算机使用智能体的感知失效

ToolSafe 提出步骤级护栏 TS-Guard 与 TS-Flow，降低 Agent 有害工具调用

BrowseSafe：研究者构建浏览器 Agent 提示注入基准并评测现有防御