Watermarking Techniques for Large Language Models: A Survey

TL;DR

This survey comprehensively reviews watermarking techniques for large language models, analyzing traditional and multimodal methods, their advantages and challenges, and proposing directions for future research and innovation in the field.

Contribution

First thorough review of LLM watermarking, analyzing inheritance from traditional techniques and exploring multimodal watermarking, with insights into challenges and future prospects.

Findings

Analyzes traditional and current LLM watermarking techniques.

Examines multimodal watermarking for visual and audio data.

Identifies challenges and future directions in LLM watermarking.

Abstract

With the rapid advancement and extensive application of artificial intelligence technology, large language models (LLMs) are extensively used to enhance production, creativity, learning, and work efficiency across various domains. However, the abuse of LLMs also poses potential harm to human society, such as intellectual property rights issues, academic misconduct, false content, and hallucinations. Relevant research has proposed the use of LLM watermarking to achieve IP protection for LLMs and traceability of multimedia data output by LLMs. To our knowledge, this is the first thorough review that investigates and analyzes LLM watermarking technology in detail. This review begins by recounting the history of traditional watermarking technology, then analyzes the current state of LLM watermarking research, and thoroughly examines the inheritance and relevance of these techniques. By analyzing their inheritance and relevance, this review can provide research with ideas for applying traditional digital watermarking techniques to LLM watermarking, to promote the cross-integration and innovation of watermarking technology. In addition, this review examines the pros and cons of LLM watermarking. Considering the current multimodal development trend of LLMs, it provides a detailed analysis of emerging multimodal LLM watermarking, such as visual and audio data, to offer more reference ideas for relevant research. This review delves into the challenges and future prospects of current watermarking technologies, offering valuable insights for future LLM watermarking research and applications.