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

Oct 12 · Monday

All papers

Found 36 papers

Filter5

Attack type

Jailbreaks10 Prompt injection19 Detection evasion7

Attack technique

Automated search6 Encoding and obfuscation3 Defense-targeted6 Dormant triggers3

Defense type

Detection and filtering20 Permissions and approval3

Impact

Harmful content9 Unauthorized actions11 Output manipulation11

System component

MCP and skills23 Memory31 RAG18 Guardrails and judges36 Monitors19 Reasoning chains5 Permissions and sandboxing23 Fine-tuning and open weights4 Vision6 Embeddings4 Multimodal7

Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 233papers have no tags yet and are not included in filtered results.

Attack surface / entry point：User input Attack surface / entry point：Documents and messages Attack surface / entry point：Weights and gradients Layer：Application layer System component：Guardrails and judges Clear all

Another 233papers 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
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
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
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 2610.04412Oct 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
DefensesarXiv 2610.02432Oct 2
论文提出 LLM 输入扰动鲁棒性度量，并发布 ASA 攻击与 AttestMCP 防护
提出 ASA 与 AttestMCP，度量并降低 LLM 对输入序列扰动的敏感
arXiv
2610.02432
Published
Oct 2
Layer
Application layer
Setting
LLM applications, AI Agent
Attacker
Black-box
Evaluated models
Gemma-3-27B-Instruct, Gemma-3-4B-Instruct, Llama-3.2-3B-Instruct and others12
- DefensesDetection and filtering
- AttacksDetection evasion
- ComponentGuardrails and judges
Paper analysisRead analysis
DefensesarXiv 2609.33039Sep 27
TACIT: detecting agent trajectory harm from LLM internal states
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
DefensesarXiv 2609.30657Sep 25
研究者提出面向邮件 Agent 的攻击链建模提示注入检测框架
提出面向邮件 Agent 的攻击链提示注入检测框架
arXiv
2609.30657
Published
Sep 25
Layer
Application layer
Setting
AI Agent
Evaluated models
Proposed framework
- DefensesDetection and filtering
- AttacksPrompt injection
- ComponentGuardrails and judges
Abstract攻击链与动作一致性融合改善了严格检测的平均 F1，但迁移、误报和攻击召回仍需分别看。
这是一项邮件智能体提示注入防御的离线建模与评测研究：作者把攻击文本是否恶意、攻击是否推进到工具操作、最终参数是否达标分开处理。
Paper analysisRead analysis
AttacksarXiv 2609.29130Sep 24
ClaimMirage：域名中的自我声明如何改变 LLM 威胁判断
提出 ClaimMirage，以域名自述声称改变 LLM 威胁告警判断
arXiv
2609.29130
Published
Sep 24
Layer
Application layer
Setting
LLM applications
Evaluated models
Llama 3.3 70B Instruct-Turbo, Gemma 3 4B it, Gemma 3 12B it and others5
- AttacksDetection evasion
- ComponentGuardrails and judges
Abstract作者称自述声称可增减告警。
Paper analysisRead analysis
AttacksarXiv 2609.22510Sep 19
特拉维夫大学提出爆炸性提示词：条件触发的间接提示注入可绕过九款生产 Agent
提出条件触发的爆炸提示词，并设计摄入期检测器 DeFuse
arXiv
2609.22510
Published
Sep 19
Layer
Application layer
Setting
AI Agent
Evaluated models
Llama-3.1-8B-Instruct, Llama-3.1-70B-Instruct, Qwen2.5-32B-Instruct and others15
- DefensesDetection and filtering
- AttacksPrompt injection
- TechniqueDormant triggers
- ComponentGuardrails and judges
Abstract论文揭示了条件触发使提示注入绕过防御并在触发时执行工具，提出轻量检测器并在摄入期有效防范。
论文针对大语言模型智能体面临的间接提示注入威胁，研究了利用条件句式实现时间分离的爆炸提示词。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.15017Sep 14
PIDS-Bench：在过度防御、混淆与分布偏移下评测提示注入检测器
提出 PIDS-Bench，评测提示注入检测器在过度防御与分布偏移下的表现
arXiv
2609.15017
Published
Sep 14
Layer
Application layer
Setting
LLM applications
Evaluated models
TF-IDF + logistic regression, DistilBERT, DeBERTa-v3-FT and others7
- DefensesDetection and filtering
- AttacksPrompt injection
- ComponentGuardrails and judges
AbstractPIDS-Bench 显示高分布内 F1 仍会过度拦截外部来源的安全相关良性输入。
PIDS-Bench 是一个冻结的检测器级基准，用来在固定阈值下同时看提示注入检测和良性误报。
Paper analysisRead analysis
DefensesarXiv 2609.13601Sep 12
Mind the Gap：检测 DAO 治理中的描述-执行不匹配攻击
提出 DEMI 检测框架，用生命周期模拟和证据映射发现 DAO 提案错配
arXiv
2609.13601
Published
Sep 12
Layer
Application layer
Setting
LLM applications
Evaluated models
GPT-4o, GPT-4o-mini, GPT-4.1 and others9
- DefensesDetection and filtering
- ComponentGuardrails and judges
Abstract作者把 DAO 错配检测做成执行前审计层，主张逐动作证据映射与风险复核是关键。
这是面向 DAO 治理的执行前错配检测研究：攻击者可以提交看似合理的描述，但让获批载荷执行另一种行为，投票描述并不直接约束代码。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2608.17445Aug 18
Paper: decomposition attacks can bypass LLM stateful defenses across unlinkable identities
形式化跨不可关联身份的分解攻击并评测状态化防御边界
arXiv
2608.17445
Published
Aug 18
Layer
Application layer
Setting
LLM applications
Evaluated models
Granite Guardian 3.1 2B
- AttacksJailbreaks
- ComponentGuardrails and judges
Paper analysisRead analysis
AttacksarXiv 2608.16246Aug 17
CompoSkill 框架利用逐个通过扫描的 Agent 技能组合发起攻击
提出 CompoSkill，将逐个通过扫描的技能编排为攻击链
arXiv
2608.16246
Published
Aug 17
Layer
Application layer
Setting
AI Agent
Evaluated models
GPT-5.4, Gemini-3.1-flash, DeepSeek-V4 and others4
- AttacksPrompt injection
- TechniqueDefense-targeted
- ComponentMCP and skills
Abstract论文分析了智能体技能组合风险，指出单包安全认证状态不具备可组合性，需转向路径级防护。
Paper analysisRead analysis
DefensesarXiv 2608.06422Aug 6
CMU 研究：分片判断可避免 LLM 监督失效并抵御对抗利用
提出分片监督，将评判标准分配给独立调用以抵御展示攻击
arXiv
2608.06422
Published
Aug 6
Layer
Application layer
Setting
LLM applications
Attacker
Black-box
Evaluated models
Claude Opus 4.8, Claude Sonnet 4.6, Claude Opus 4.6 and others4
- DefensesDetection and filtering
- AttacksDetection evasion
- ComponentGuardrails and judges
Abstract论文揭示决策负载是大模型监督的独立瓶颈，提出分片与辩论机制有效分离注意力与平衡证据，在多项高难度基准上实现稳健评判。
本文系统研究了大语言模型在执行多标准监督与评判时的决策负载瓶颈及其安全风险。
Paper analysisRead analysis
AttacksarXiv 2608.03844Aug 4
MAFIA：针对带审计 LLM Agent 的查询式记忆投毒攻击
提出 MAFIA，以探测放置与事实伪装对带审计 Agent 做查询式记忆投毒
arXiv
2608.03844
Published
Aug 4
Layer
Application layer
Setting
AI Agent
Evaluated models
gpt-5.4-mini, Gemini, ProtectAI and others8
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentMemory
Paper analysisRead analysis
DefensesarXiv 2607.21642Jul 22
CARE: Pre-execution command validation for LLM agents that execute shell commands
Proposes a static-first validator, CARE, that decides before dispatch whether an agent's shell command may be executed
arXiv
2607.21642
Published
Jul 22
Layer
Application layer
Setting
coding agent
- DefensesPermissions and approval
- AttacksPrompt injection
- ComponentPermissions and sandboxing
Paper analysisRead analysis
DefensesarXiv 2608.12361Jul 5
基于搜索增强 LLM 的中文新词毒性共识检测框架 SeTox
提出 SeTox 检索增强框架，检测中文新词的隐性毒性
arXiv
2608.12361
Published
Jul 5
Layer
Application layer
Setting
LLM applications
Evaluated models
SeTox-Qwen2.5-7B
- DefensesDetection and filtering
- AttacksDetection evasion
- ComponentGuardrails and judges
AbstractSeTox 用检索把公共共识接入静态 LLM，以检测中文毒性新词。
SeTox 研究中文新词上的隐性毒性检测：词表加检索增强，使静态 LLM 在不重训练的情况下利用公开网页上下文。
Paper analysisRead analysis
AttacksarXiv 2606.14517Jun 12
Researchers disclose a reasoning-amplified denial-of-service attack against LLM agent guardrails
提出针对 Agent 护栏的推理扩展拒绝服务攻击
arXiv
2606.14517
Published
Jun 12
Layer
Application layer
Setting
AI Agent
Attacker
Black-box
Evaluated models
TS-Guard-8B, Qwen3.5-9B, DeepSeek-V3.2 and others11
- AttacksDenial of service
- TechniqueReasoning-chain manipulation
- ComponentGuardrails and judges
Paper analysisRead analysis

AI Safety Daily

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

All papers

Attack type

Attack technique

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

BRANCH 方法绕过 6 套多扫描器护栏系统

DEFER1 多智能体防御研究报告受控测试中的攻击成功率下降

CRIME 框架利用良性 Agent 技能组合诱发恶意行为

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

论文提出 LLM 输入扰动鲁棒性度量，并发布 ASA 攻击与 AttestMCP 防护

TACIT: detecting agent trajectory harm from LLM internal states

研究者提出面向邮件 Agent 的攻击链建模提示注入检测框架

ClaimMirage：域名中的自我声明如何改变 LLM 威胁判断

特拉维夫大学提出爆炸性提示词：条件触发的间接提示注入可绕过九款生产 Agent

PIDS-Bench：在过度防御、混淆与分布偏移下评测提示注入检测器

Mind the Gap：检测 DAO 治理中的描述-执行不匹配攻击

Paper: decomposition attacks can bypass LLM stateful defenses across unlinkable identities

CompoSkill 框架利用逐个通过扫描的 Agent 技能组合发起攻击

CMU 研究：分片判断可避免 LLM 监督失效并抵御对抗利用

MAFIA：针对带审计 LLM Agent 的查询式记忆投毒攻击

CARE: Pre-execution command validation for LLM agents that execute shell commands

基于搜索增强 LLM 的中文新词毒性共识检测框架 SeTox

Researchers disclose a reasoning-amplified denial-of-service attack against LLM agent guardrails