Can I read Towards Copyright Protection for Knowledge Bases of Retrieval-augmented Language Models via Ownership Verification with Reasoning on EtoBox?

Towards Copyright Protection for Knowledge Bases of Retrieval-augmented Language Models via Ownership Verification with Reasoning by Guo, Junfeng; Li, Yiming; Chen, Ruibo; Wu, Yihan; Liu, Chenxi; Chen, Yanshuo; Huang, Heng is a scholarly article available to read on EtoBox.

What is Towards Copyright Protection for Knowledge Bases of Retrieval-augmented Language Models via Ownership Verification with Reasoning about?

Large language models (LLMs) are increasingly integrated into real-world applications through retrieval-augmented generation (RAG) mechanisms to supplement their responses with up-to-date and domain-specific knowledge. However, the valuable and often proprietary nature of the knowledge bases used in RAG introduces the risk of unauthorized usage by adversaries. Existing methods that can be generalized as watermarking techniques to protect these knowledge bases typically involve poisoning attacks. However, these methods require to alter the results of verification samples (\eg, generating incorrect outputs), inevitably making them susceptible to anomaly detection and even introduce new security risks. To address these challenges, we propose \name{} for `harmless' copyright protection of knowledge bases. Instead of manipulating LLM's final output, \name{} implants distinct verification behaviors in the space of chain-of-thought (CoT) reasoning, maintaining the correctness of the final answer. Our method has three main stages: (1) \textbf{Generating CoTs}: For each verification question, we generate two CoTs, including a target CoT for building watermark behaviors; (2) \textbf{Optimizi

Author

Guo, Junfeng; Li, Yiming; Chen, Ruibo; Wu, Yihan; Liu, Chenxi; Chen, Yanshuo; Huang, Heng

Published

2025

Language

EN