Who Stole Your Data? A Method for Detecting Unauthorized RAG Theft
By: Peiyang Liu , Ziqiang Cui , Di Liang and more
Potential Business Impact:
Protects AI writing from being stolen.
Retrieval-augmented generation (RAG) enhances Large Language Models (LLMs) by mitigating hallucinations and outdated information issues, yet simultaneously facilitates unauthorized data appropriation at scale. This paper addresses this challenge through two key contributions. First, we introduce RPD, a novel dataset specifically designed for RAG plagiarism detection that encompasses diverse professional domains and writing styles, overcoming limitations in existing resources. Second, we develop a dual-layered watermarking system that embeds protection at both semantic and lexical levels, complemented by an interrogator-detective framework that employs statistical hypothesis testing on accumulated evidence. Extensive experimentation demonstrates our approach's effectiveness across varying query volumes, defense prompts, and retrieval parameters, while maintaining resilience against adversarial evasion techniques. This work establishes a foundational framework for intellectual property protection in retrieval-augmented AI systems.
Similar Papers
Secure Retrieval-Augmented Generation against Poisoning Attacks
Cryptography and Security
Stops bad info from tricking smart computer programs.
Secure Retrieval-Augmented Generation against Poisoning Attacks
Cryptography and Security
Stops bad info from tricking smart computer programs.
Private-RAG: Answering Multiple Queries with LLMs while Keeping Your Data Private
Machine Learning (CS)
Keeps private information safe when computers answer questions.