Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kim, San, Kim, Jonghwi, Jeon, Yejin, Lee, Gary Geunbae
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2507.18202
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Inhaltsangabe:
  • Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by providing external knowledge for accurate and up-to-date responses. However, this reliance on external sources exposes a security risk, attackers can inject poisoned documents into the knowledge base to steer the generation process toward harmful or misleading outputs. In this paper, we propose Gradient-based Masked Token Probability (GMTP), a novel defense method to detect and filter out adversarially crafted documents. Specifically, GMTP identifies high-impact tokens by examining gradients of the retriever's similarity function. These key tokens are then masked, and their probabilities are checked via a Masked Language Model (MLM). Since injected tokens typically exhibit markedly low masked-token probabilities, this enables GMTP to easily detect malicious documents and achieve high-precision filtering. Experiments demonstrate that GMTP is able to eliminate over 90% of poisoned content while retaining relevant documents, thus maintaining robust retrieval and generation performance across diverse datasets and adversarial settings.