# data-attacks
標記為「data-attacks」的 15 篇文章
RAG & Data Attack Assessment (Assessment)
Assessment on RAG poisoning, embedding attacks, training data extraction, and membership inference.
Lab: Advanced RAG Poisoning
Hands-on lab for crafting documents that reliably get retrieved and influence RAG responses for specific target queries.
Lab: Chunking Exploitation
Hands-on lab for crafting documents that split across chunks in ways that hide malicious content from chunk-level filtering while maintaining attack effectiveness.
Lab: Citation Fabrication
Hands-on lab for getting RAG systems to cite documents that don't exist or misattribute quotes to legitimate sources.
Lab: RAG Metadata Injection
Hands-on lab for exploiting metadata fields like titles, descriptions, and timestamps to manipulate RAG retrieval ranking and influence responses.
Lab: RAG Pipeline Poisoning
Hands-on lab for setting up a RAG pipeline with LlamaIndex, injecting malicious documents, testing retrieval poisoning, and measuring injection success rates.
Lab: Re-ranking Attacks
Hands-on lab for manipulating the re-ranking stage of RAG pipelines to promote or suppress specific documents in retrieval results.
章節評量：RAG 攻擊
15 題校準評量，測試你對 RAG 管線攻擊的理解——知識庫投毒、檢索操控與資料萃取。
RAG & Data 攻擊 評量 (評量)
評量 on RAG poisoning, embedding attacks, training data extraction, and membership inference.
實驗室: 進階 RAG 投毒
Hands-on lab for crafting documents that reliably get retrieved and influence RAG responses for specific target queries.
實驗室: Chunking 利用ation
Hands-on lab for crafting documents that split across chunks in ways that hide malicious content from chunk-level filtering while maintaining attack effectiveness.
實驗室: Citation Fabrication
Hands-on lab for getting RAG systems to cite documents that don't exist or misattribute quotes to legitimate sources.
實驗室: RAG Metadata Injection
Hands-on lab for exploiting metadata fields like titles, descriptions, and timestamps to manipulate RAG retrieval ranking and influence responses.
實驗室: RAG Pipeline 投毒
Hands-on lab for setting up a RAG pipeline with LlamaIndex, injecting malicious documents, testing retrieval poisoning, and measuring injection success rates.
實驗室: Re-ranking 攻擊s
Hands-on lab for manipulating the re-ranking stage of RAG pipelines to promote or suppress specific documents in retrieval results.