Evaluating Durability: Benchmark Insights into Image and Text Watermarking

Jielin Qiu, William Han, Xuandong Zhao, Shangbang Long, Christos Faloutsos, Lei Li

Abstract: As large models become increasingly prevalent, watermarking has emerged as a crucial technology for copyright protection, authenticity verification, and content tracking. The rise of multimodal applications further amplifies the importance of effective watermarking techniques. While watermark robustness is critical for real-world deployment, the current understanding of watermark robustness against various forms of corruption remains limited. Our study evaluates watermark robustness in both image and text domains, testing against an extensive set of 100 image perturbations and 63 text perturbations. The results reveal significant vulnerabilities in contemporary watermarking approaches - detection accuracy deteriorates by more than 50\% under common perturbations, highlighting a critical gap between current capabilities and practical requirements. These findings emphasize the urgent need for more robust watermarking methods that can withstand real-world disturbances. Our project website can be found at https://mmwatermark-robustness.github.io/.

Keywords: image and text watermarking, robustness, image corruptions and text perturbations, multimodal

Changes Since Last Submission: Replaced the paper title with the author list on the top of each even page

Code: https://github.com/Jielin-Qiu/MMWatermark-Robustness

Assigned Action Editor: ~Hongyang_Zhang1

Submission Number: 70