RAG Security

Vector database security, retrieval poisoning, and embedding attacks

Resources: 2

Newest first · 2 reviewed on this page

paper2024arXiv preprintReviewed

PoisonedRAG: Knowledge Poisoning Attacks to Retrieval-Augmented Generation of Large Language Models

Wei Zou, Runpeng Geng, Binghui Wang +1

Demonstrates knowledge poisoning attacks against RAG systems where adversaries inject malicious texts into the knowledge database to manipulate LLM outputs.

Data Poisoning RAG SecurityOpen access85 cit.

paper2024arXiv preprintReviewed

ConfusedPilot: Confused Deputy Risks in RAG-based LLMs

Ayush RoyChowdhury, Mulong Luo, Prateek Sahu +2

Introduces confused deputy attacks against RAG-based code assistants like GitHub Copilot, where poisoned code repositories manipulate assistant outputs.

RAG Security Supply Chain Attacks Agentic ThreatsOpen access25 cit.