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

Oct 12 · Monday

All papers

Found 10 papers

Filter4

Attack type

Prompt injection10 Poisoning and backdoors3

Impact

Unauthorized actions5 Output manipulation4

System type

LLM applications20 AI Agent132 coding agent10 web agent7 Browser and computer use4 Multi-agent systems10

Attack surface / entry point

User input11 Documents and messages6 Tool responses5 Tool and skill descriptions3 Retrieval corpus3 Memory writes6 Inter-agent messages25

Layer

Application layer10

System component

Memory3

Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 254papers have no tags yet and are not included in filtered results.

System type：Multi-agent systems Attack surface / entry point：Documents and messages Attack surface / entry point：Tool responses Layer：Application layer Clear all

Another 254papers 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 2610.05640Oct 5
Research reveals that the CaMeL defense fails in multi-agent systems and proposes multi-CaMeL
提出 multi-CaMeL，在智能体调用边界隔离可信指令与非可信数据
arXiv
2610.05640
Published
Oct 5
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
Claude Fable 5, GPT-5.5, GPT-4.1 and others6
- DefensesInstruction–data separation
- AttacksPrompt injection
Abstract论文针对多智能体中单体防御不组合的边界清洗问题，提出 multi-CaMeL 协议彻底阻断了 MultiAgentDojo 上的注入攻击。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.39146Sep 30
MADBench：多智能体辩论安全性评测基准发布
提出 MADBench，评测多智能体辩论是吸收还是放大对抗影响
arXiv
2609.39146
Published
Sep 30
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
gpt-4o, GPT-5, GPT-6 Astra
- AttacksPrompt injection
- ComponentRAG
AbstractMADBench 显示辩论能吸收部分准确率攻击，同时放大未授权读写。
MADBench 是一个评测多智能体辩论安全性的基准，用来看攻击是被辩论吸收还是被放大。
Paper analysisRead analysis
AttacksarXiv 2609.38270Sep 29
VirusCascade：劫持 LLM 推荐智能体的协同反思机制
提出 VirusCascade，联合操纵商品描述与交互轨迹以劫持推荐智能体协同反思
arXiv
2609.38270
Published
Sep 29
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
AgentCF, AgentSEQ, AgentRAG and others4
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentMemory
Abstract作者把反思写回视为推广攻击入口，并用联合操纵和诊断探针研究其持续与传播。
VirusCascade 是针对推荐智能体协作反思的 black-box targeted promotion 攻击研究。 攻击者只改商品描述和少量账号的普通交互，试图让目标商品获得更多良性用户曝光。
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
Evaluation and benchmarksarXiv 2609.24662Sep 21
DUMA-Bench：评估 LLM Agent 安全的双控多智能体基准
提出双控多智能体基准 DUMA-Bench，测量对抗环境下的策略违反
arXiv
2609.24662
Published
Sep 21
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
GPT-5, GPT-5-mini, GPT-5-nano and others14
- AttacksPrompt injection
AbstractDUMA-Bench 用双控交互评测智能体安全。
DUMA-Bench 把 τ²-bench 的双控交互做成智能体安全评测，用来看策略违反如何随用户、模型和环境一起出现。
Paper analysisRead analysis
DefensesarXiv 2609.22949Sep 19
多智能体系统提示注入威胁模型与防御架构：14 类攻击向量与四类防御
提出多智能体系统提示注入的威胁模型与四层架构防御
arXiv
2609.22949
Published
Sep 19
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
GPT-4o (2024-08-06), Claude 3.5 Sonnet, Llama 3 70B-Instruct
- DefensesInstruction–data separation
- AttacksPrompt injection
- ComponentPermissions and sandboxing
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.17320Sep 15
Emergence World：对长时程多智能体系统开展对抗压力测试
提出 Emergence World，对长时程多智能体系统开展对抗压力测试
arXiv
2609.17320
Published
Sep 15
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
Claude Opus 4.8, DeepSeek v4 Pro, Gemini 3.5 Flash and others9
- AttacksPrompt injection
- RiskMisalignment and value divergence
- ComponentMemory
Abstract作者通过长期平行世界实验指出模型对齐不具备可组合性，单模型群体会产生社会奉承、协同退缩及语言不透明等失效。
Paper analysisRead analysis
AttacksarXiv 2606.12918Jun 11
MAStrike：用 Shapley 值引导多智能体系统协同红队攻击
提出 MAStrike，用 Shapley 选联盟对多智能体做共谋红队
arXiv
2606.12918
Published
Jun 11
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
Claude Opus 4.7, GPT-5.5, Gemini 3.1 Pro
- AttacksPrompt injection
- TechniqueAutomated search
Paper analysisRead analysis
DefensesarXiv 2603.04474Mar 4
从火花到烈火：建模并缓解基于 LLM 的多智能体协作中的错误级联
提出谱系图治理层抑制多智能体协作的错误级联
arXiv
2603.04474
Published
Mar 4
Layer
Application layer
Setting
Multi-agent systems
- DefensesDetection and filtering
- AttacksPrompt injection
- RiskHallucination and fabrication
- ComponentGuardrails and judges
Abstract单一种子可沿固定协作图固化为错误共识。
作者把 LLM-MAS 中“小错变成集体错误共识”做成图上的可测传播，并用只改消息、不改拓扑的插件压低最终感染。
Paper analysisRead analysis

You have reached the end

AI Safety Daily

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