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.

Attack surface / entry point：User input Attack surface / entry point：Web pages and interfaces Attack surface / entry point：Documents and messages Attack surface / entry point：Training data Layer：Application layer System component：RAG 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
DefensesarXiv 2610.07276Oct 6
SAFESHIELD：小语言模型部署时安全的决策组织框架
提出 SAFESHIELD，组织小语言模型部署时的安全决策
arXiv
2610.07276
Published
Oct 6
Layer
Application layer
Setting
LLM applications
Evaluated models
Qwen3-4B-Instruct
- AttacksJailbreaks
- RiskHallucination and fabrication
- ComponentRAG
AbstractSAFESHIELD 用可审计决策轨迹组织 SLM 部署时的四项安全决策，并报告协调依赖影响端到端结果。
SAFESHIELD 是面向小语言模型的部署时安全框架，把运行时安全从单项审核改写成可检查的决策过程。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.05586Oct 5
AgentDoxx：联网搜索 Agent 对匿名访谈文本的再识别评测
构建 AGENTDOXX 基准，评测联网搜索 Agent 对匿名访谈的再识别
arXiv
2610.05586
Published
Oct 5
Layer
Application layer
Setting
web agent
Evaluated models
GPT-5.6 Terra, GPT-5 Mini, GPT-4.1 Mini and others10
- AttacksMalicious use
- ComponentRAG
Abstract论文提出了已知身份的重识别基准 AGENTDOXX，揭示搜索与记忆双重风险及现有防御在检索轨迹中的泄露漏洞。
Paper analysisRead analysis
AttacksarXiv 2610.01871Oct 1
研究者提出 IMMRAG 攻击，可从多模态 RAG 数据存储中提取医学与文档图像
提出 imMRAG 攻击，从多模态 RAG 私有图像库提取内容
arXiv
2610.01871
Published
Oct 1
Layer
Application layer
Setting
LLM applications
Attacker
Black-box
Evaluated models
Lumina-mGPT, Gemini 2.5 Flash Image Preview, CLIP ViT-B/16 and others5
- AttacksExtraction and theft
- TechniqueCross-modal payloads
- ComponentRAG
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
DefensesarXiv 2609.36326Sep 29
PILLAR：面向增强检索的私有倒排索引词法查找
提出 PILLAR，用私有词法预筛与客户端重排保护 RAG 查询
arXiv
2609.36326
Published
Sep 29
Layer
Application layer
Setting
LLM applications
- ComponentRAG
AbstractPILLAR 用固定模式的私有 BM25 预筛加本地嵌入重排，在两基准上换取延迟或质量。
PILLAR 是面向公开语料的隐私 RAG：半诚实服务器学不到查询词项和访问模式，客户端仍拿到用于增强生成的 k 篇文档。
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
AttacksarXiv 2609.14649Sep 14
CIG-MIA：利用上下文信息增益对 RAG 系统发起成员推断攻击
提出 CIG-MIA，用上下文信息增益推断 RAG 知识库成员身份
arXiv
2609.14649
Published
Sep 14
Layer
Application layer
Setting
LLM applications
Attacker
Gray-box, Black-box
Evaluated models
Llama-3.1-8B-Instruct, Mistral-7B-Instruct-v0.3, Llama-2-13b-chat-hf and others6
- AttacksExtraction and theft
- ComponentRAG
AbstractCIG-MIA 用注入前后的答案似然差推断 RAG 库成员，灰盒可分性高于所列基线。
CIG-MIA 是针对 RAG 外部知识库的成员推断攻击，同时覆盖灰盒和纯文本黑盒。
Paper analysisRead analysis
AttacksarXiv 2609.12448Sep 11
GraphProfiler 用个人知识图谱推断敏感属性并溯源到具体帖子
提出 GraphProfiler，用个人知识图谱从帖子历史推断敏感属性并溯源
arXiv
2609.12448
Published
Sep 11
Layer
Application layer
Setting
LLM applications
- AttacksMalicious use
- ComponentRAG
AbstractGraphProfiler 用源链接个人知识图谱做属性推断，准确率接近文本基线，并把证据定位到少量源帖。
GraphProfiler 是一个可审计的 LLM 敏感属性画像器：用源链接个人知识图谱，把推断落到具体帖子。
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 2608.17829Aug 18
LeakGauge：用行为探针在解码前检测上下文泄露攻击信号
提出 LeakGauge，用行为后缀的 prefill 对数概率检测上下文泄露
arXiv
2608.17829
Published
Aug 18
Layer
Application layer
Setting
LLM applications
Attacker
Black-box
Evaluated models
Gemma-4-E4B-it, Gemma-4-31B-it, Qwen2.5-14B-Instruct and others11
- DefensesDetection and filtering
- AttacksExtraction and theft
- ComponentRAG
Paper analysisRead analysis
AttacksarXiv 2608.04565Aug 5
Researchers propose Breadcrumbing long-range attack that can hijack the evidence chain of DeepResearch-style search agents
提出权威链劫持与轨迹引导策略演化，劫持搜索 Agent 的证据链
arXiv
2608.04565
Published
Aug 5
Layer
Application layer
Setting
web agent
Evaluated models
Qwen3.5-9B, Gemma4-31B, DeepResearch and others7
- AttacksPrompt injection
- TechniqueAutomated search
- ComponentRAG
Abstract论文揭示了多步搜索智能体在受限中间人操纵下的脆弱性，提出 ACH 策略与 TGSE 演化方法并完成系统验证。
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 2605.24312May 23
MEntA 用 5 次查询实现 RAG 成员推断攻击
提出 MEntA，用非模板查询推断文档是否属于 RAG 检索库
arXiv
2605.24312
Published
May 23
Layer
Application layer
Setting
LLM applications
Attacker
Black-box
Evaluated models
Phi4-14B, Llama3.1-8B, CommandR-7B and others5
- AttacksExtraction and theft
- ComponentRAG
Paper analysisRead analysis
DefensesarXiv 2605.19847May 19
论文揭示多租户 RAG 账号合谋使隐私泄露随账号数线性增长
提出零知识审计协议，核验多租户 RAG 的合谋差分隐私
arXiv
2605.19847
Published
May 19
Layer
Application layer
Setting
LLM applications
- AttacksExtraction and theft
- ComponentRAG
Abstract揭示多租户 RAG 合谋泄露按根号 k 放大，提出带零知识证明的无泄露审计协议。
论文针对多租户 RAG 服务在多账户协同攻击下隐私边界失效的问题展开研究。
Paper analysisRead analysis
AttacksarXiv 2603.25164Mar 26
PIDP-Attack: Combining Prompt Injection and Database Poisoning to Attack RAG Systems
Proposes PIDP-Attack, which manipulates RAG answers using query suffixes and corpus poisoning
arXiv
2603.25164
Published
Mar 26
Layer
Application layer
Setting
LLM applications
Evaluated models
qwen/qwen2.5-7b-instruct, qwen/qwen2-7b-instruct, meta/llama-3.1-8b-instruct and others8
- AttacksPrompt injection
- TechniqueSelection manipulation
- ComponentRAG
Paper analysisRead analysis
AttacksarXiv 2603.17239Mar 18
LAAF: A Systematic Red-Teaming Method and Automated Attack Framework for LPCI Vulnerabilities in Agentic LLM Systems
Proposes LAAF, which automatically attacks LPCI vulnerabilities in agent systems in stages
arXiv
2603.17239
Published
Mar 18
Layer
Application layer
Setting
AI Agent
Evaluated models
gemini-2.0-flash-001, claude-3-haiku-20240307, meta-llama/llama-3.1-70b-instruct and others5
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentMemory
AbstractLAAF does LPCI red teaming with taxonomy plus stage seeding.
The authors state that LAAF is an automated red-teaming framework built specifically for LPCI in agentic LLMs. The issue to address is that encoded, delayed, and conditionally triggered payloads can persist in memory or RAG and re-enter across sessions, whereas Garak and PyRIT do not use the previous round's breakthrough results to seed the next stage across the six stages.
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2602.16752Feb 18
Vulnerability of LLM Re-rankers to Prompt Injection Attacks
测量 LLM 重排序器对文档内提示注入的脆弱性
arXiv
2602.16752
Published
Feb 18
Layer
Application layer
Setting
LLM applications
Evaluated models
Qwen3-0.6B, Qwen3-1.7B, Qwen3-8B and others16
- AttacksPrompt injection
- ComponentRAG
Abstract复现 DOH/DCH 对 LLM 重排序器的影响，并给出规模、位置、架构和领域上的边界。
Paper analysisRead analysis
AttacksarXiv 2602.15654Feb 17
Zombie Agent: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injection
提出 Zombie Agent 攻击，经网页间接注入将载荷写入长期记忆并跨会话触发
arXiv
2602.15654
Published
Feb 17
Layer
Application layer
Setting
AI Agent
Evaluated models
Gemini-2.5-Flash, GLM-4.7-Flash
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentMemory
Abstract记忆写入把一次网页间接注入变成跨会话控制。
Zombie Agent 把自进化 LLM 智能体的跨会话记忆当成攻击面：攻击者只发布网页，良性任务读入后，正常记忆更新留下载荷，并在以后无关会话里触发未授权工具行为。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2602.09319Feb 10
Benchmarking Knowledge Extraction Attacks and Defenses in RAG
建立 RAG 知识抽取攻防基准，统一评测抽取攻击与防御
arXiv
2602.09319
Published
Feb 10
Layer
Application layer
Setting
LLM applications
Evaluated models
GPT-4o, GPT-4o-mini, Llama3-8B-Instruct and others8
- AttacksExtraction and theft
- ComponentRAG
Abstract统一基准比较 RAG 知识抽取攻防，作者称检索与生成都要优化，单一防御不能完全防护。
作者给出一个比较 RAG 知识抽取攻击与防御的统一基准。
Paper analysisRead analysis

AI Safety Daily

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