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

Oct 12 · Monday

All papers

Found 49 papers

Filter5

Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 232papers have no tags yet and are not included in filtered results.

Impact：Output manipulation Layer：Application layer System component：Memory System component：RAG System component：Embeddings Clear all

Another 232papers 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 2610.07645Oct 6
SkillPoison：用成功经验投毒自进化 Agent 的技能形成
提出 SkillPoison，用局部有效的成功经验诱导自进化 Agent 形成过度泛化技能
arXiv
2610.07645
Published
Oct 6
Layer
Application layer
Setting
AI Agent
Evaluated models
deepseek-v4-flash, Qwen V3.8 Flash, GPT-5.5
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentMemory
AbstractSkillPoison 通过局部有效且验证成功的经验诱导技能过度泛化，在多个评测基准上实现了持久的下游攻击影响。
SkillPoison 提出了一种针对自进化智能体经验到技能形成过程的攻击范式，通过组织已验证的成功经验诱导技能过度泛化。
Paper analysisRead analysis
DefensesarXiv 2610.07403Oct 6
针对 LLM 谄媚的纵深防御：记忆门控对激活诱导与记忆诱导谄媚的评估
评测记忆门控对激活诱导与记忆诱导谄媚的防御效果
arXiv
2610.07403
Published
Oct 6
Layer
Application layer
Setting
LLM applications
Evaluated models
Llama-3.1-8B-Instruct, Qwen2.5-7B-Instruct, Mistral-7B-Instruct-v0.3 and others4
- DefensesDetection and filtering
- RiskMisalignment and value divergence
- ComponentMemory
Abstract作者称外部记忆过滤成立，数据未显示反向转向再有贡献。
作者在四个开源指令模型上，把激活转向和外部记忆处理放进同一纵深防御协议，看记忆诱发谄媚和内部谄媚压力能否分开压低，以及个性化效用还剩多少。要处理的问题是：检索到的用户历史会推动模型顺从存储信念。只改外部上下文，并不直接动模型内部的谄媚表征。
Paper analysisRead analysis
DefensesarXiv 2610.05826Oct 5
研究者提出临时可见性协议，限制持续摄入 RAG 向量库的投毒暴露
提出临时可见性协议，限制持续摄入 RAG 向量库的投毒暴露
arXiv
2610.05826
Published
Oct 5
Layer
Application layer
Setting
LLM applications
- DefensesInstruction–data separation
- AttacksPoisoning and backdoors
- ComponentRAG
Abstract用截止期限制未核验可见时长。
这篇工作给持续摄入的 RAG 向量库一个失败关闭的临时可见性协议，把协议能限制的未核验暴露和依赖检测器的中毒暴露分开。
Paper analysisRead analysis
DefensesarXiv 2610.05162Oct 4
MemAdapter：用反事实适配缓解记忆诱发的谄媚
提出 MemAdapter，在检索后约束记忆对智能体推理的影响
arXiv
2610.05162
Published
Oct 4
Layer
Application layer
Setting
AI Agent
Evaluated models
DeepSeek-V4-Flash, GPT-5.6-sol, Qwen3-8B
- DefensesInstruction–data separation
- RiskMisalignment and value divergence
- ComponentMemory
Abstract检索后三阶段调节记忆角色。
MemAdapter 是给长期记忆智能体用的检索后调节框架，用来处理记忆诱发谄媚。
Paper analysisRead analysis
AttacksarXiv 2610.02373Oct 2
HDI 攻击：篡改 GraphRAG 辅助结构可致 88–94% 攻击成功率
提出 HDI 攻击以篡改 GraphRAG 辅助结构破坏检索
arXiv
2610.02373
Published
Oct 2
Layer
Application layer
Setting
LLM applications
Evaluated models
Microsoft GraphRAG, HippoRAG2
- AttacksPoisoning and backdoors
- ComponentRAG
Abstract论文形式化了 GraphRAG 辅助模式级实体攻击面，提出 HDI 攻击并验证其攻击效果。
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 2609.36130Sep 29
论文提出 DerivAudit：审计长期 Agent 记忆是否真由交互历史支持
提出 DERIVAUDIT 审计长期 Agent 记忆是否由交互历史导出
arXiv
2609.36130
Published
Sep 29
Layer
Application layer
Setting
AI Agent
Evaluated models
Qwen3-30B-A3B, Gemma-4-31B, Llama-3.3-70B-Instruct
- RiskHallucination and fabrication
- ComponentMemory
AbstractDERIVAUDIT 表明扩历史能补出处，但组合准入与过细检查仍两侧出错。
DERIVAUDIT 审计长期智能体的持久记忆是否由写入时可获得的交互历史支持，而不是只看以后能否被召回。
Paper analysisRead analysis
AttacksarXiv 2609.35155Sep 28
LENS：检索增强生成中集合级投毒的整体危害大于各部分之和
提出 LENS，构造集合级 RAG 语料投毒以导向预设答案
arXiv
2609.35155
Published
Sep 28
Layer
Application layer
Setting
LLM applications
Evaluated models
Qwen3.6-35B-A3B, Llama-3.1-70B-Instruct, DeepSeek-V4-Pro
- AttacksPoisoning and backdoors
- TechniqueAutomated search
- ComponentRAG
Paper analysisRead analysis
AttacksarXiv 2609.37468Sep 26
论文提出针对 Agentic RAG 的检索器后门攻击与 DOU 隐藏方法
提出检索器后门攻击操纵智能体搜索，并用 DOU 逃避检测
arXiv
2609.37468
Published
Sep 26
Layer
Application layer
Setting
AI Agent
Evaluated models
E5, Contriever-MSMARCO
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentRAG
Abstract论文展示了通过恶意检索器操纵智能体多轮搜索并利用诱饵重塑表征隐蔽后门的可行性与系统风险。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.31342Sep 25
Research reveals outdated document poisoning: RAG retrieval can make models abandon originally correct answers
评测 RAG 中过期文档推翻模型原本正确回答的现象
arXiv
2609.31342
Published
Sep 25
Layer
Application layer
Setting
LLM applications
Evaluated models
GPT-4o, GPT-4.1, Claude-Opus-4.5 and others13
- ComponentRAG
Abstract论文评测了陈旧检索推翻正确知识的中毒现象，并分析了其内部机制与防御局限。
这篇论文是对检索增强生成（RAG）中“陈旧文档中毒”现象的实证与机理评估研究。
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 2609.02774Sep 3
CodePoisonRAG：针对检索增强代码生成的知识投毒攻击
提出 CodePoisonRAG，对检索增强代码生成的知识库投毒以植入漏洞
arXiv
2609.02774
Published
Sep 3
Layer
Application layer
Setting
LLM applications
Evaluated models
Qwen 3.5 9B, Code Llama 13B, DeepSeek-Coder-V2 16B
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentRAG
AbstractCodePoisonRAG 展示了 RACG 外部知识库的新攻击面，在较低投毒率下可定向诱发指定漏洞并部分抵御防御。
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
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
AttacksarXiv 2609.01325Sep 1
VerTox：用可验证奖励引导的强化学习对神经排序模型实施语料投毒
提出 VerTox，用可验证奖励强化学习生成误导文档并投毒检索语料
arXiv
2609.01325
Published
Sep 1
Layer
Application layer
Setting
LLM applications
Evaluated models
SimLM-base, BGE-base, Cohere-embed-english-v3.0 and others8
- AttacksPoisoning and backdoors
- TechniqueAutomated search
- ComponentRAG
AbstractVerTox 以可验证奖励微调小 LLM，生成能抬高排序并腐蚀事实的投毒文档。
VerTox 用可验证奖励把小 LLM 微调成语料投毒生成器，用来探测神经排序器在注入文档下的暴露面。
Paper analysisRead analysis
AttacksarXiv 2608.23471Aug 25
InjecMEM: Memory Injection Attacks against LLM Agent Memory Systems
提出 InjecMEM，一次注入 Agent 记忆使后续查询输出预设内容
arXiv
2608.23471
Published
Aug 25
Layer
Application layer
Setting
AI Agent
Evaluated models
Qwen2.5-7B-Instruct, Llama-3.1-8B-Instruct, Mistral-7B-Instruct-v0.3 and others6
- AttacksPoisoning and backdoors
- TechniqueGradient and representation optimization
- ComponentMemory
Paper analysisRead analysis
DefensesarXiv 2608.10502Aug 11
依赖引导回滚修复：为记忆增强 Agent 恢复错误记忆后的答案与状态
提出依赖引导回滚修复，恢复记忆增强 Agent 的回答与状态
arXiv
2608.10502
Published
Aug 11
Layer
Application layer
Setting
AI Agent
Evaluated models
GPT-4o, Gemini-3.6-Flash, Qwen3.6-27B
- DefensesInstruction–data separation
- AttacksPoisoning and backdoors
- ComponentMemory
Paper analysisRead analysis
Risky behaviorarXiv 2608.10218Aug 11
研究者用进化算法构造多智能体 LLM 系统中的自我传播“思维病毒”
用演化算法构造 mind virus 并测量其在多智能体中的传播
arXiv
2608.10218
Published
Aug 11
Layer
Application layer
Setting
Multi-agent systems, coding agent
Evaluated models
Claude Haiku 4.5, Claude Sonnet 4.6, Gemini 3 Flash and others7
- RiskMisalignment and value divergence
- ComponentMemory
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

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

SkillPoison：用成功经验投毒自进化 Agent 的技能形成

针对 LLM 谄媚的纵深防御：记忆门控对激活诱导与记忆诱导谄媚的评估

研究者提出临时可见性协议，限制持续摄入 RAG 向量库的投毒暴露

MemAdapter：用反事实适配缓解记忆诱发的谄媚

HDI 攻击：篡改 GraphRAG 辅助结构可致 88–94% 攻击成功率

MADBench：多智能体辩论安全性评测基准发布

VirusCascade：劫持 LLM 推荐智能体的协同反思机制

论文提出 DerivAudit：审计长期 Agent 记忆是否真由交互历史支持

LENS：检索增强生成中集合级投毒的整体危害大于各部分之和

论文提出针对 Agentic RAG 的检索器后门攻击与 DOU 隐藏方法

Research reveals outdated document poisoning: RAG retrieval can make models abandon originally correct answers

Emergence World：对长时程多智能体系统开展对抗压力测试

CodePoisonRAG：针对检索增强代码生成的知识投毒攻击

Counter-GEO-Bench：现有护栏难挡 GEO 虚假信息

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

VerTox：用可验证奖励引导的强化学习对神经排序模型实施语料投毒

InjecMEM: Memory Injection Attacks against LLM Agent Memory Systems

依赖引导回滚修复：为记忆增强 Agent 恢复错误记忆后的答案与状态

研究者用进化算法构造多智能体 LLM 系统中的自我传播“思维病毒”