Enhancing LLM Watermark Resilience Against Both Scrubbing and Spoofing Attacks

Watermarking is a promising defense against the misuse of large language models (LLMs), yet it remains vulnerable to scrubbing and spoofing attacks. This vulnerability stems from an inherent trade-off governed by watermark window size: smaller windows resist scrubbing better but are easier to reverse-engineer, enabling low-cost statistics-based spoofing attacks.

This work expands the trade-off boundary by introducing a novel mechanism, equivalent texture keys, where multiple tokens within a watermark window can independently support the detection.

Based on the redundancy, we propose a watermark scheme with Sub-vocabulary decomposed Equivalent tExture Key (SEEK). It achieves a Pareto improvement, increasing the resilience against scrubbing attacks without compromising robustness to spoofing.

Our code will be available at https://github.com/Hearum/SeekWM.