Robust Multi-bit Natural Language Watermarking through Invariant Features

TL;DR

This paper proposes a robust multi-bit natural language watermarking method that leverages invariant features and a corruption-resistant infill model to enhance robustness against minor corruptions, aiding copyright protection.

Contribution

It introduces a novel watermarking framework that improves robustness by 16.8% using invariant feature analysis and a new infill model for natural language content.

Findings

Achieved +16.8% robustness improvement over previous methods

Effective watermark extraction despite minor corruptions

Applicable across multiple datasets and corruption types

Abstract

Recent years have witnessed a proliferation of valuable original natural language contents found in subscription-based media outlets, web novel platforms, and outputs of large language models. However, these contents are susceptible to illegal piracy and potential misuse without proper security measures. This calls for a secure watermarking system to guarantee copyright protection through leakage tracing or ownership identification. To effectively combat piracy and protect copyrights, a multi-bit watermarking framework should be able to embed adequate bits of information and extract the watermarks in a robust manner despite possible corruption. In this work, we explore ways to advance both payload and robustness by following a well-known proposition from image watermarking and identify features in natural language that are invariant to minor corruption. Through a systematic analysis of the possible sources of errors, we further propose a corruption-resistant infill model. Our full method improves upon the previous work on robustness by +16.8% point on average on four datasets, three corruption types, and two corruption ratios. Code available at https://github.com/bangawayoo/nlp-watermarking.