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

Oct 13 · Tuesday

All papers

Found 22 papers

Filter5

Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 215papers have no tags yet and are not included in filtered results.

System type：LLM applications System type：Multi-agent systems Attack surface / entry point：Web pages and interfaces Attack surface / entry point：Memory writes Attack surface / entry point：Training data Clear all

Another 215papers do not have category tags yet and are not included in filtered results.

AttacksarXiv 2610.11932Oct 8
A Fudan team measures the citation fragility of AI search: ordinary posts can enter citations and answer text
Measures citation fragility in AI search, demonstrating that ordinary public posts can enter citations and answers.
arXiv
2610.11932
Published
Oct 8
Layer
Application layer
Setting
LLM applications
Evaluated models
Grok, Doubao, ChatGPT and others10
- AttacksPoisoning and backdoors
- ComponentRAG
AbstractThe authors claim the paper quantifies vulnerabilities in AI search caused by citation preferences and low posting thresholds; tests show public web posts can penetrate AI citations, and they call for auditing the citation supply chain.
Paper analysisRead analysis
AttacksarXiv 2610.10000Oct 7
超越奖励压制：有界奖励热启动 Bandit 的近最优离线攻击
提出热启动 Bandit 的部署前有界离线注入攻击
arXiv
2610.10000
Published
Oct 7
Layer
Training and data layer
Setting
LLM applications
Evaluated models
UCB, Thompson Sampling, ϵ-greedy
- AttacksPoisoning and backdoors
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
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
AttacksarXiv 2609.39788Sep 30
研究：多智能体系统潜在通信链路可被训练用于提升有害顺从
提出只训练或篡改多智能体潜在通信链路来提高有害遵从
arXiv
2609.39788
Published
Sep 30
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
Llama-3.2-3B-Instruct, Qwen2.5-3B-Instruct, Gemma-3-1B-IT and others7
- AttacksModel tampering
- TechniqueGradient and representation optimization
Abstract潜在链路本身即可改变冻结智能体系统的安全，奖励既能攻击也能修复。
学习得到的潜在通信链路会改变由冻结、对齐智能体组成的系统是否遵从有害请求。。作者研究三种拓扑：双智能体、三级顺序协作，以及双专家加汇总。
Paper analysisRead analysis
DefensesarXiv 2610.00371Sep 30
FlowReview：以授权配对评测控制多智能体组合信息流
提出 FlowReview，用授权配对与确定性提交门控控制多智能体组合信息流
arXiv
2610.00371
Published
Sep 30
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
Sonnet 4.5, Haiku 4.5, Qwen3-32B and others5
- DefensesPermissions and approval
- AttacksPrompt injection
- ComponentPermissions and sandboxing
Abstract配对标准要求拒绝禁止使用并完成授权使用，FlowReview 把三项审查接到执行。
这篇工作把多智能体安全写成一件必须同时成立的事：拦住组合信息所启用的禁止使用，并完成同一场景里任务所需的授权使用。
Paper analysisRead analysis
DefensesarXiv 2609.21088Sep 18
Provenance-Aware Transformers：用来源感知架构分离可信边界以防御间接提示注入
提出 Provenance-Aware Transformers，隔离不可信来源防御间接提示注入
arXiv
2609.21088
Published
Sep 18
Layer
Application layer
Setting
LLM applications
Evaluated models
SmolLM2-360M-Instruct, LLaMA-3-8B-Instruct, Qwen2.5-7B-Instruct and others4
- DefensesInstruction–data separation
- AttacksPrompt injection
Paper analysisRead analysis
DefensesarXiv 2609.17648Sep 15
多智能体 LLM 流水线中的信任传播与结构隔离
用任务绑定令牌和策略预言机拦住多智能体流水线的未授权执行
arXiv
2609.17648
Published
Sep 15
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
gemma4:31b-cloud
- DefensesPermissions and approval
- AttacksPoisoning and backdoors
- ComponentPermissions and sandboxing
Abstract结构性授权拦住了记忆投毒的未授权执行，持密钥时承重的是策略预言机。
作者在一条会改写沙箱邮件库的四智能体流水线上，检查低权限失陷会不会变成未授权的真实动作。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.02316Sep 2
Counter-GEO-Bench：现有护栏难挡 GEO 虚假信息
构建 COUNTER-GEO-BENCH，评测生成式搜索中的 GEO 虚假信息防御
arXiv
2609.02316
Published
Sep 2
Layer
Application layer
Setting
LLM applications
Evaluated models
Gemma-4-31B-IT, Qwen-3.5-35B-A3B, Llama-4-Scout-17B-16E and others8
- DefensesDetection and filtering
- AttacksPrompt injection
- ComponentRAG
Abstract论文构建了针对 GEO 虚假信息的首个防御基准，揭示通用护栏的失效与反作用，并提出了有效的轻量对比检测基线。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.05535Sep 2
Mind2Web-Injection：面向网页 Agent 视觉提示注入护栏的证据对齐评测
提出 Mind2Web-Injection 评测网页 Agent 视觉注入护栏
arXiv
2609.05535
Published
Sep 2
Layer
Application layer
Setting
LLM applications
Evaluated models
GPT-5.6-luna, Qwen3-VL-32B, Qwen3-VL-8B and others6
- DefensesDetection and filtering
- AttacksPrompt injection
- ComponentGuardrails and judges
Abstract作者称检测、定位和反事实响应在六个 VLM 上可分开。
Mind2Web-Injection 用来检查网页截图护栏的判决是否对齐到该用的画面证据。。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2608.16824Aug 18
GEO-Flag：检测与测量面向生成式引擎优化的网页内容
提出 GEOFlagBench 与 IPT，检测并测量生成式引擎优化网页
arXiv
2608.16824
Published
Aug 18
Layer
Application layer
Setting
LLM applications
Evaluated models
ModernBERT-base, Qwen3-0.6B, Gemini-3.5-flash and others11
- DefensesDetection and filtering
- ComponentGuardrails and judges
AbstractGEOFlagBench 与 IPT 用于检测 GEO 页，并估计真实检索中的占比与引用可核验性。
GEO-Flag 把页面级 GEO 检测做成可评测任务，并在发布的检索结果上估计被判为 GEO 的页面占比。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2608.03272Aug 4
多智能体协同过滤系统的连接性攻击与防御研究
复现 AgentCF 上的多智能体攻防并刻画连通性作用
arXiv
2608.03272
Published
Aug 4
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
Qwen3-235B-A22B, Claude Haiku 4.5, Mixtral 8×7B and others4
- AttacksPoisoning and backdoors
- ComponentMemory
Abstract连通性沿 k 与ρ改变攻防，且用户/物品与早期/稳态需要分开看。
作者在 AgentCF 上研究连通性如何改变多智能体协同过滤的攻防，复现已有方法而不是提出新载荷。
Paper analysisRead analysis
AttacksarXiv 2608.00718Aug 1
研究揭示多智能体 LLM 流水线的结构性漏洞
提出多智能体流水线的边界攻击，使对抗内容作为可信输入跨层传播
arXiv
2608.00718
Published
Aug 1
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
GPT-5-mini, Claude Sonnet 4.5, Kimi K2.5
- AttacksPrompt injection
Abstract缺边界校验使对抗内容跨智能体传播，作者称这是架构属性而非模型能力。
作者把多智能体 LLM 流水线的对抗问题定义为缺少边界校验，并用生产轨迹和受控实验检查脆弱性来自架构还是骨干模型。中间输出未经验证就传给下游。作者认为，一旦某级接受对抗内容，后续智能体会把它当作可信输入。
Paper analysisRead analysis
AttacksarXiv 2605.24421May 23
研究者提出日志型提示注入攻击，可抑制 SOC 中 LLM 分析助手的恶意日志识别
提出日志基底提示注入，操纵 SOC 分析员的分类、摘要与处置建议
arXiv
2605.24421
Published
May 23
Layer
Application layer
Setting
LLM applications
Evaluated models
gpt-4o-mini
- AttacksPrompt injection
- TechniqueConversation structure manipulation
Abstract在 gpt-4o-mini 上，人格劫持与上下文操纵可改写 SOC 分析输出，直接覆盖在分类上无效。
Paper analysisRead analysis
AttacksarXiv 2605.08460May 9
论文建模多智能体网络中的子智能体继承攻击面
建模并利用多智能体网络中子智能体生成时的记忆继承漏洞
arXiv
2605.08460
Published
May 9
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
MiniMax M2.5, Llama-4-Maverick-17B-128E-Instruct-FP8, Qwen3.5-Plus and others5
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentMemory
Abstract形式化子智能体继承，在 OpenClaw 上演示四类编排层漏洞并提出防御。
作者对多智能体网络里的子智能体继承做形式化分析，并用开源框架上的 PoC 演示编排层如何让单点妥协继续扩散。
Paper analysisRead analysis
AttacksarXiv 2604.03890Apr 5
From prompts to physical actions: structured backdoor attacks against LLM-mediated robot control systems
Propose a structured JSON backdoor that triggers malicious actions in robot control via a poisoned LoRA
arXiv
2604.03890
Published
Apr 5
Layer
Training and data layer
Setting
Embodied systems and robotics, LLM applications
Evaluated models
Llama-3.1-8B-Instruct, Gemma-2-9B-IT, DeepSeek-R1-Distill-Llama-8B and others4
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentFine-tuning and open weights
Abstract推理层后门传不到执行。
Paper analysisRead analysis
AttacksarXiv 2602.15344Feb 17
ER-MIA: Black-box Adversarial Memory Injection Attacks against Long-term Memory-augmented Large Language Models
提出 ER-MIA 黑盒记忆注入，用嵌入相近记忆抢占检索并改错后续回答
arXiv
2602.15344
Published
Feb 17
Layer
Application layer
Setting
LLM applications
Evaluated models
Llama3.2:3b, Gemma 3:27b, GPT-oss:20b
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentMemory
Paper analysisRead analysis
AttacksarXiv 2602.06409Feb 6
VENOMREC: Cross-modal Interactive Poisoning for Targeted Promotion in Multimodal LLM Recommendation Systems
提出 VenomRec 跨模态交互投毒，定向推广多模态推荐物品
arXiv
2602.06409
Published
Feb 6
Layer
Training and data layer
Setting
LLM applications
Evaluated models
VIP5 (T5-small), VIP5 (T5-base), DiffMM
- AttacksPoisoning and backdoors
- TechniqueCross-modal payloads
- ComponentVision
Paper analysisRead analysis
AttacksarXiv 2602.05484Feb 5
Masked Mirror: Covert Prompt Injection Attacks Against LLM-Based Phishing Detection
提出隐蔽提示注入攻击 LLM 钓鱼检测器，并给出防御 InjectDefuser
arXiv
2602.05484
Published
Feb 5
Layer
Application layer
Setting
LLM applications
Evaluated models
OpenAI GPT-5, xAI Grok 4 Fast (Non-Reasoning), Meta Llama 4 Maverick and others4
- DefensesInstruction–data separation
- AttacksPrompt injection
- TechniqueEncoding and obfuscation
- ComponentGuardrails and judges
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2601.10923Jan 16
Hidden-in-Plain-Text: A benchmark for indirect prompt injection in social network RAG
用 OpenRAG-Soc 评测社交网页 RAG 的间接提示注入与检索投毒
arXiv
2601.10923
Published
Jan 16
Layer
Application layer
Setting
LLM applications
Evaluated models
Llama-3-8B-Instruct, Mistral-7B-Instruct, Qwen2.5-14B and others8
- AttacksPrompt injection
- TechniqueEncoding and obfuscation
- ComponentRAG
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

Attack surface / entry point

Layer

System component

A Fudan team measures the citation fragility of AI search: ordinary posts can enter citations and answer text

超越奖励压制：有界奖励热启动 Bandit 的近最优离线攻击

DEFER1 多智能体防御研究报告受控测试中的攻击成功率下降

Research reveals that the CaMeL defense fails in multi-agent systems and proposes multi-CaMeL

研究：多智能体系统潜在通信链路可被训练用于提升有害顺从

FlowReview：以授权配对评测控制多智能体组合信息流

Provenance-Aware Transformers：用来源感知架构分离可信边界以防御间接提示注入

多智能体 LLM 流水线中的信任传播与结构隔离

Counter-GEO-Bench：现有护栏难挡 GEO 虚假信息

Mind2Web-Injection：面向网页 Agent 视觉提示注入护栏的证据对齐评测

GEO-Flag：检测与测量面向生成式引擎优化的网页内容

多智能体协同过滤系统的连接性攻击与防御研究

研究揭示多智能体 LLM 流水线的结构性漏洞

研究者提出日志型提示注入攻击，可抑制 SOC 中 LLM 分析助手的恶意日志识别

论文建模多智能体网络中的子智能体继承攻击面

From prompts to physical actions: structured backdoor attacks against LLM-mediated robot control systems

ER-MIA: Black-box Adversarial Memory Injection Attacks against Long-term Memory-augmented Large Language Models

VENOMREC: Cross-modal Interactive Poisoning for Targeted Promotion in Multimodal LLM Recommendation Systems

Masked Mirror: Covert Prompt Injection Attacks Against LLM-Based Phishing Detection

Hidden-in-Plain-Text: A benchmark for indirect prompt injection in social network RAG