Abstract
Digital image watermarking is increasingly critical in media contexts, as emerging regulations and industry practices require marking AI-generated content and ensuring traceable sources to prevent manipulation or misuse. Recent advances in invisible watermarking methods highlight the need to update existing benchmarking practices to reflect current techniques and evaluation criteria. We address this by introducing WARP -- a unified framework and benchmark for evaluating the robustness of invisible watermarks. WARP incorporates 32 recent classical, deep, and generative watermarking methods, as well as 34 different erasing techniques, ranging from traditional distortions to more sophisticated adversarial, purification, and re-embedding attacks. It provides standardized, reproducible, and easily scalable protocols for evaluating perceptual quality, watermark readability, and attack resilience. Using WARP, we extensively evaluate current invisible watermarking techniques, collecting the largest robustness benchmark in the field. Results identify the most robust approaches under both distortion and adversarial conditions, and reveal consistent relationships between watermarking methods and the attack strategies most effective against them. Our experiments also highlight that some of the watermarking methods considered are highly vulnerable to reembedding, even if they are robust to standard distortions. The code is made available at https://github.com/ispras/wibe.
Keywords
Publication details
- DOI
- 10.1145/3767308.3835888
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Abud, K., Yakushev, A., Akimenkov, A., Serzhenko, I., Aistov, K., Kovalev, E., Obydenkov, D., Lavrushkin, S., Antsiferova, A., Vatolin, D., Markin, Y., & Lukianov, K. (2026). WARP: A Unified Benchmark for Invisible Image Watermarking -- Robustness and Protection Against Attacks. https://doi.org/10.1145/3767308.3835888
MLA 9
Abud, Khaled, et al. "WARP: A Unified Benchmark for Invisible Image Watermarking -- Robustness and Protection Against Attacks." https://doi.org/10.1145/3767308.3835888.
Chicago (author–date)
Abud, Khaled, Aleksey Yakushev, Aleksandr Akimenkov, Irina Serzhenko, Kirill Aistov, Egor Kovalev, Dmitry Obydenkov, Sergey Lavrushkin, Anastasia Antsiferova, Dmitriy Vatolin, Yury Markin, and Kirill Lukianov. 2026. "WARP: A Unified Benchmark for Invisible Image Watermarking -- Robustness and Protection Against Attacks." https://doi.org/10.1145/3767308.3835888.
Harvard
Abud, K., Yakushev, A., Akimenkov, A., Serzhenko, I., Aistov, K., Kovalev, E., Obydenkov, D., Lavrushkin, S., Antsiferova, A., Vatolin, D., Markin, Y. and Lukianov, K. (2026) 'WARP: A Unified Benchmark for Invisible Image Watermarking -- Robustness and Protection Against Attacks', doi:10.1145/3767308.3835888.
Vancouver
Abud K, Yakushev A, Akimenkov A, Serzhenko I, Aistov K, Kovalev E, et al. WARP: A Unified Benchmark for Invisible Image Watermarking -- Robustness and Protection Against Attacks. doi:10.1145/3767308.3835888
IEEE
K. Abud, A. Yakushev, A. Akimenkov, I. Serzhenko, K. Aistov, E. Kovalev, D. Obydenkov, S. Lavrushkin, A. Antsiferova, D. Vatolin, Y. Markin, and K. Lukianov, "WARP: A Unified Benchmark for Invisible Image Watermarking -- Robustness and Protection Against Attacks," doi: 10.1145/3767308.3835888.