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

Oct 13 · Tuesday

All papers

Found 12 papers

Filter1

Attack type

Prompt injection6

Impact

Output manipulation6

System type

LLM applications9 AI Agent3

Attack surface / entry point

User input3 Retrieval corpus5

Layer

Application layer12

System component

MCP and skills17 Memory31 RAG12 Guardrails and judges69 Monitors29 Reasoning chains11 Permissions and sandboxing12 Fine-tuning and open weights5 Vision33 Audio11 Video8 Image generation7 Multimodal52

Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 201papers have no tags yet and are not included in filtered results.

System component：RAG Clear all

Another 201papers do not have category tags yet and are not included in filtered results.

Evaluation and benchmarksarXiv 2610.08571Oct 6
RAG-PIBench：可信 RAG 系统中提示注入检测的泄漏感知基准
提出 RAG-PIBench，评测 RAG 上下文中提示注入检测器
arXiv
2610.08571
Published
Oct 6
Layer
Application layer
Setting
LLM applications
Evaluated models
DistilBERT-base-uncased, DeBERTa-v3-base, MiniLM
- DefensesDetection and filtering
- AttacksPrompt injection
- ComponentRAG
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
Evaluation and benchmarksarXiv 2610.04691Oct 4
RAGStress：评测知识库退化下 RAG 鲁棒性的受控基准
提出 RAGStress 受控基准，评测知识库退化下的 RAG
arXiv
2610.04691
Published
Oct 4
Layer
Application layer
Setting
LLM applications
Evaluated models
Claude Sonnet 4, Claude Opus 4.6, DeepSeek R1 and others5
- ComponentRAG
Abstract作者用 RAGStress 比较五系统。
RAGStress 是知识库损坏下的 RAG 受控压力测试。作者明确不把它当作模型排行榜。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.01218Oct 1
AGO AI Quality Gate：面向 RAG 的证据优先发布决策框架
提出面向 RAG 的证据优先发布框架 AGO，并评测评审 adherence 判别
arXiv
2610.01218
Published
Oct 1
Layer
Application layer
Setting
LLM applications
Evaluated models
gpt-4o, gpt-4.1-nano
- ComponentGuardrails and judges
AbstractAGO 把缺失证据和评审误差写成显式发布状态，并要求按领域验证评审。
AGO 是部署在企业 RAG 评估业务中的自托管发布门控，用来决定一个版本应放行、人工复核还是拦截。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.39146Sep 30
MADBench: multi-agent debate safety evaluation benchmark released
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
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 2609.02316Sep 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 2607.20891Jul 23
MisKnow-Agent 评测
用 MisKnow-Agent 评测深度研究智能体是否采纳误导文档结论
arXiv
2607.20891
Published
Jul 23
Layer
Application layer
Setting
web agent
Evaluated models
DeerFlow, WebThinker, Gemini Deep Research and others6
- AttacksPrompt injection
- ComponentRAG
Abstract论文通过 MisKnow-Agent 框架评估发现长程研究智能体易采纳误导性知识，且现有防御难以完全消除该现象。
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
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
Evaluation and benchmarksarXiv 2601.13227Jan 20
Insider knowledge: How much can RAG systems gain from evaluation secrets?
测量 RAG 系统利用评测秘密抬高自动评测分数的程度
arXiv
2601.13227
Published
Jan 20
Layer
Application layer
Setting
LLM applications
- RiskReward hacking
- ComponentRAG
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

You have reached the end

AI Safety Daily

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