Skip to content

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

Oct 12 · Monday

All papers

Found 8 papers
Filter4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 233papers have no tags yet and are not included in filtered results.

Another 233papers do not have category tags yet and are not included in filtered results.

  1. 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
  2. AttacksarXiv 2608.04565

    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

    Published
    Setting
    web agent
    Evaluated models
    Qwen3.5-9B, Gemma4-31B, DeepResearch and others7

    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
  3. 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
  4. 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
You have reached the end