{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/the-efficacy-of-transfer-based-no-box-attacks","title":"The Efficacy of Transfer-based No-box Attacks on Image Watermarking: A Pragmatic Analysis","arxiv_id":"2412.02576","date":"2024-12-03","proceeding":null,"authors":["Qilong Wu","Varun Chandrasekaran"],"abstract":"Watermarking approaches are widely used to identify if images being circulated are authentic or AI-generated. Determining the robustness of image watermarking methods in the ``no-box'' setting, where the attacker is assumed to have no knowledge about the watermarking model, is an interesting problem. Our main finding is that evading the no-box setting is challenging: the success of optimization-based transfer attacks (involving training surrogate models) proposed in prior work~\\cite{hu2024transfer} depends on impractical assumptions, including (i) aligning the architecture and training configurations of both the victim and attacker's surrogate watermarking models, as well as (ii) a large number of surrogate models with potentially large computational requirements. Relaxing these assumptions i.e., moving to a more pragmatic threat model results in a failed attack, with an evasion rate at most $21.1\\%$. We show that when the configuration is mostly aligned, a simple non-optimization attack we propose, OFT, with one single surrogate model can already exceed the success of optimization-based efforts. Under the same $\\ell_\\infty$ norm perturbation budget of $0.25$, prior work~\\citet{hu2024transfer} is comparable to or worse than OFT in $11$ out of $12$ configurations and has a limited advantage on the remaining one. The code used for all our experiments is available at \\url{https://github.com/Ardor-Wu/transfer}.","url_abs":"https://arxiv.org/abs/2412.02576v1","url_pdf":"https://arxiv.org/pdf/2412.02576v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"the-efficacy-of-transfer-based-no-box-attacks","repo_url":"https://github.com/ardor-wu/transfer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}