Abstract
Invisible watermarking has become a central tool for tracing AI-generated images, but its robustness against adaptive removal attacks remains an open security question. We introduce Latent Frequency Masking, an attack that erases watermark evidence by replacing selected Fourier coefficients in the latent representation of a watermarked image. The replacement can be sampled from Gaussian noise for efficiency or derived from diffusion regeneration for improved image preservation. We provide a theoretical distortion bound relating the change between the reconstructed adversarial image and the masked latent-frequency perturbation. We evaluate the proposed attack against six diffusion watermarking methods on images generated from DiffusionDB and MS-COCO prompts. Latent Frequency Masking removes or substantially weakens several watermarks while preserving perceptual quality and achieving favorable runtime compared with existing attacks. These results identify latent-frequency manipulation as a practical attack surface and highlight the need to include such attacks in robustness evaluations of generative image watermarking.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Aistov, K., Abud, K., Serzhenko, I., Kovalev, E., Yakushev, A., Akimenkov, A., Obydenkov, D., Markin, Y., Lavrushkin, S., Vatolin, D., & Antsiferova, A. (2026). Exploring Weaknesses of Generative Image Watermarks against Latent Frequency Masking. https://omanscience.com/en/articles/exploring-weaknesses-of-generative-image-watermarks-against-latent-frequency-masking
MLA 9
Aistov, Kirill, et al. "Exploring Weaknesses of Generative Image Watermarks against Latent Frequency Masking." https://omanscience.com/en/articles/exploring-weaknesses-of-generative-image-watermarks-against-latent-frequency-masking.
Chicago (author–date)
Aistov, Kirill, Khaled Abud, Irina Serzhenko, Egor Kovalev, Aleksey Yakushev, Aleksandr Akimenkov, Dmitry Obydenkov, Yury Markin, Sergey Lavrushkin, Dmitriy Vatolin, and Anastasia Antsiferova. 2026. "Exploring Weaknesses of Generative Image Watermarks against Latent Frequency Masking." https://omanscience.com/en/articles/exploring-weaknesses-of-generative-image-watermarks-against-latent-frequency-masking.
Harvard
Aistov, K., Abud, K., Serzhenko, I., Kovalev, E., Yakushev, A., Akimenkov, A., Obydenkov, D., Markin, Y., Lavrushkin, S., Vatolin, D. and Antsiferova, A. (2026) 'Exploring Weaknesses of Generative Image Watermarks against Latent Frequency Masking', Available at: https://omanscience.com/en/articles/exploring-weaknesses-of-generative-image-watermarks-against-latent-frequency-masking.
Vancouver
Aistov K, Abud K, Serzhenko I, Kovalev E, Yakushev A, Akimenkov A, et al. Exploring Weaknesses of Generative Image Watermarks against Latent Frequency Masking. https://omanscience.com/en/articles/exploring-weaknesses-of-generative-image-watermarks-against-latent-frequency-masking
IEEE
K. Aistov, K. Abud, I. Serzhenko, E. Kovalev, A. Yakushev, A. Akimenkov, D. Obydenkov, Y. Markin, S. Lavrushkin, D. Vatolin, and A. Antsiferova, "Exploring Weaknesses of Generative Image Watermarks against Latent Frequency Masking," https://omanscience.com/en/articles/exploring-weaknesses-of-generative-image-watermarks-against-latent-frequency-masking.