Skip to content

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

Oct 13 · Tuesday

All papers

Found 23 papers

Another 227papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2610.11932

    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.

    Published
    Evaluated models
    Grok, Doubao, ChatGPT and others10

    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
  2. DefensesarXiv 2610.05826

    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

    Published
    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
  3. 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

    Published
    Evaluated models
    gpt-4o, GPT-5, GPT-6 Astra
    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
  4. AttacksarXiv 2609.37468

    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

    Published
    Setting
    AI Agent
    Evaluated models
    E5, Contriever-MSMARCO

    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
  5. AttacksarXiv 2609.02774

    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

    Published
    Evaluated models
    Qwen 3.5 9B, Code Llama 13B, DeepSeek-Coder-V2 16B

    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
  6. AttacksarXiv 2609.01325

    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

    Published
    Evaluated models
    SimLM-base, BGE-base, Cohere-embed-english-v3.0 and others8
    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
  7. AttacksarXiv 2607.00422

    KidnapRAG:黑盒投毒攻击劫持 Agentic RAG 的推理链

    提出 KidnapRAG,用投毒文档黑盒劫持 Agentic RAG 的推理链

    Published
    Setting
    AI Agent
    Evaluated models
    Qwen2.5-32B-Instruct, Llama-3.3-70B-Instruct, QwQ-32B and others5
    Abstract顺序投毒可把多步推理拖向指定应答,作者称关键在持续引导而非单次注入。

    KidnapRAG 是针对 Agentic RAG 的 black-box 语料投毒:攻击者不能访问模型、提示词、检索器或私有轨迹,只能发布可能被检索的文档,并利用公开界面上的推理与搜索查询。

    Paper analysisRead analysis
  8. AttacksarXiv 2606.11265

    论文提出 CRCP 投毒框架,揭示 RAG 分块与重排序下的投毒失效问题

    提出 CRCP 框架,优化分块与重排下的 RAG 语料投毒

    Published
    Evaluated models
    GPT-4o, DeepSeek-R1, Qwen3-Max and others11
    AbstractCRCP 把投毒做成多阶段一致性问题。

    CRCP 研究的是带分块和重排的 RAG 语料投毒,而不是只提高文档级检索分数。

    Paper analysisRead analysis
  9. AttacksarXiv 2606.01212

    DiscourseFlip:针对黑盒 RAG 的话语级观点操纵攻击

    提出 DiscourseFlip,用有限文档投毒操纵黑盒 RAG 的话语级观点

    Published
    Evaluated models
    Llama3.1-8B-Instruct, Qwen3-8B-Instruct, BGE and others5
    AbstractDiscourseFlip 按语义图分配投毒预算。

    DiscourseFlip 是针对黑盒 RAG 的话语级观点操纵。作者要处理的缺口是:只打单条查询或主题局部查询时,覆盖窄,目标受审查时容易被隔离,也难沿相关话题传播。攻击者不能看检索器或 LLM 内部,也不能改提示词模板,只能在文档数、生成 token 和 SEO 编辑距离限制下注入少量文档。

    Paper analysisRead analysis
  10. AttacksarXiv 2605.28074

    SilentRetrieval: Hijacking retrieval-augmented generation with semantically preserved adversarial data poisoning

    提出 SilentRetrieval,以语义保持对抗文档投毒劫持 RAG 检索与生成

    Published
    Evaluated models
    Llama-2-7B-Chat, Mistral-7B-Instruct-v0.2, Qwen-7B-Chat and others10
    Abstract两阶段投毒在单文档协议下兼顾检索劫持、生成操纵与近良性困惑度。

    SilentRetrieval 是针对 RAG 的两阶段语料投毒,在每查询一篇、合成目标答案的统一协议下,同时处理检索劫持、生成操纵和流畅度。

    Paper analysisRead analysis
  11. AttacksarXiv 2603.17239

    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

    Published
    Setting
    AI Agent
    Evaluated models
    gemini-2.0-flash-001, claude-3-haiku-20240307, meta-llama/llama-3.1-70b-instruct and others5
    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
  12. AttacksarXiv 2603.03919

    When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking Attacks in RAG

    提出 TabooRAG,用单篇文档迁移阻断 RAG 对良性查询的回答

    Published
    Evaluated models
    Llama-3-8B-Instruct, Ministral-3-8B-Instruct-2512, Gemma-3-12B-it and others9
    AbstractTabooRAG 用代理侧风险文档迁移阻断 RAG。

    TabooRAG 是面向 RAG 可用性的可迁移阻断攻击,不改已有文档,也不读取目标反馈。

    Paper analysisRead analysis
  13. AttacksarXiv 2602.06616

    Confundo: Learning to Generate Robust Poisoning Content for Real RAG Systems

    提出 Confundo,微调投毒生成器为 RAG 生成抗分块的鲁棒投毒内容

    Published
    Evaluated models
    Qwen3-8b, Llama3-8b, DeepSeek and others8
    AbstractConfundo uses a fine-tuned generator for RAG poisoning; the authors report attack results on three objective types: factual, opinion, and hallucination.

    Confundo turns RAG poisoning into fine-tuning: a small model generates short poison texts for target questions, which are then placed into documents that will be ingested by the knowledge base. It targets the fact that real systems chunk documents and users do not copy preset questions verbatim, weakening specialized poisoning. The attacker has no internal knowledge of the target system and cannot query it, only prepare documents to be ingested.

    Paper analysisRead analysis
  14. AttacksarXiv 2602.00364

    "Someone hid it": Query-agnostic black-box attacks against LLM retrieval

    提出查询无关黑盒攻击 DQ-A,用可迁移文末后缀降低文档检索排名

    Published
    Evaluated models
    Qwen-1.5-7B-Instruct, SFR-Embedding-Mistral, E5-Mistral-7B-Instruct and others10
    AbstractDQ-A 以无查询黑盒后缀压低 LLM 检索排名,并在 BRIGHT 上比较三种基线。

    DQ-A 是一种 query-agnostic、complete black-box 的文档隐藏攻击,对象是用最后隐层相似度匹配的 LLM 检索。

    Paper analysisRead analysis