论文研究
arxiv.org ·
微观协作投毒：一种针对 RAG 系统的分布式攻击
该论文提出 Micro-Collaborative Poisoning，将虚假目标声明分散到多篇局部可信文档中，而非集中在单一恶意段落。作者在 108 种 RAG 配置下评估，改变数据集、检索器架构、检索深度、数据库组成、投毒数据库数量和生成模型。结果显示攻击效果来自检索来源中弱对抗信号的累积，而非单一主导段落；提高 top-k 和投毒多个数据库会增加这些信号同时出现的概率，而干净数据库的多样性和更强的检索器可降低其影响。文档级投毒可见性分析表明，该攻击比直接投毒留下更弱的显式投毒特征，难以通过孤立文档检查发现。
AI推荐理由 arXiv 预印本，作者与摘要明确，实验覆盖 108 种 RAG 配置，提出并验证了一种分布式投毒攻击：将虚假目标声明拆分到多篇局部可信文档中，靠弱对抗信号累积影响下游输出。新信息在于攻击不依赖单一恶意段落，且文档级检测难以暴露；局限是仅摘要层面，未提供代码或复现细节，结论为预印本阶段。
78
正文
Computer Science > Cryptography and Security
arXiv:2609.21573 (cs)
[Submitted on 18 Sep 2026]
Title:Micro-Collaborative Poisoning: A Distributed Attack on RAG Systems
Authors:Pedro Pereira, Eva Maia, Isabel Praça
View a PDF of the paper titled Micro-Collaborative Poisoning: A Distributed Attack on RAG Systems, by Pedro Pereira and 2 other authors
View PDF
HTML (experimental)
Abstract:Retrieval-Augmented Generation (RAG) improves large language models by grounding outputs in external knowledge sources, but this dependency also creates a surface for poisoning attacks. This paper introduces Micro-Collaborative Poisoning, a distributed attack in which a false target claim is divided across multiple locally plausible documents instead of being concentrated in a single malicious passage. We evaluate the attack across 108 RAG configurations by varying dataset, retriever architecture, retrieval depth, database composition, number of poisoned databases, and generator model. The results indicate that Micro-Collaborative Poisoning is not driven by a single dominant poisoned passage, but by the accumulation of weak adversarial signals across retrieved sources. Increasing top-$k$ and poisoning multiple databases make it more likely that these signals will appear together in the retrieved context, while clean database diversity and stronger retrievers can reduce their influence. The document-level poisoning visibility analysis further shows that this threat is difficult to expose through isolated document inspection, since Micro-Collaborative Poisoning achieves downstream influence while leaving a weaker explicit poisoning signature than direct poisoning.
Comments:
Subjects:
Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)
Cite as:
arXiv:2609.21573 [cs.CR]
(or
arXiv:2609.21573v1 [cs.CR] for this version)
https://doi.org/10.48550/arXiv.2609.21573
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Pedro Pereira [view email]
[v1]
Fri, 18 Sep 2026 10:03:33 UTC (398 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Micro-Collaborative Poisoning: A Distributed Attack on RAG Systems, by Pedro Pereira and 2 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CR
new
|
recent
| 2026-09
Change to browse by:
cs
cs.AI
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)