MIRAGE: Misleading Retrieval-Augmented Generation via Black-box and Query-agnostic Poisoning Attacks
Retrieval-Augmented Generation (RAG) systems enhance LLMs with external knowledge but introduce a critical attack surface: corpus poisoning. While recent studies have demonstrated the potential of such attacks, they typically rely on impractical assumptions, such as white-box access or known user queries, thereby under
研究重點
Retrieval-Augmented Generation (RAG) systems enhance LLMs with external knowledge but introduce a critical attack surface: corpus poisoning. While recent studies have demonstrated the potential of such attacks, they typically rely on impractical assumptions, such as white-box access or known user queries, thereby under
為什麼值得關注
這個議題涉及 Crew Pocket、Crew Deck 的實作方向。可先評估現有做法,再決定是否安排小型實驗。
可以進一步驗證什麼?
- 閱讀原文,確認它解決的問題、實驗方法及適用限制
- 檢查相關功能現有做法,找出可比較的差異
- 用小型 PoC 驗證成功率、品質、延遲和實際成本
參考資料
MIRAGE: Misleading Retrieval-Augmented Generation via Black-box and Query-agnostic Poisoning Attacks ↗2026-11-12T00:00:00Z · 研究論文索引
延伸探索
相關研究
- When Sources Disagree: Accuracy-Preserving Batch Verification and the Limits of Source-Age Screening in Retrieval-Augmented Generation相同研究主題 · 2026-11-12
- Retrieval-augmented Large Language Models for automated discharge summary generation in post-surgical ICU cancer patients相同研究主題 · 2026-11-12
- Secure Domain Adaptation and Retrieval Augmented Generation for Compact Language Models Using Archived Cybersecurity Intelligence相同研究主題 · 2026-11-06