{"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/generative-autoencoders-as-watermark","title":"Invisible Image Watermarks Are Provably Removable Using Generative AI","arxiv_id":"2306.01953","date":"2023-06-02","proceeding":null,"authors":["Xuandong Zhao","Kexun Zhang","Zihao Su","Saastha Vasan","Ilya Grishchenko","Christopher Kruegel","Giovanni Vigna","Yu-Xiang Wang","Lei LI"],"abstract":"Invisible watermarks safeguard images' copyrights by embedding hidden messages only detectable by owners. They also prevent people from misusing images, especially those generated by AI models. We propose a family of regeneration attacks to remove these invisible watermarks. The proposed attack method first adds random noise to an image to destroy the watermark and then reconstructs the image. This approach is flexible and can be instantiated with many existing image-denoising algorithms and pre-trained generative models such as diffusion models. Through formal proofs and extensive empirical evaluations, we demonstrate that pixel-level invisible watermarks are vulnerable to this regeneration attack. Our results reveal that, across four different pixel-level watermarking schemes, the proposed method consistently achieves superior performance compared to existing attack techniques, with lower detection rates and higher image quality. However, watermarks that keep the image semantically similar can be an alternative defense against our attacks. Our finding underscores the need for a shift in research/industry emphasis from invisible watermarks to semantic-preserving watermarks. Code is available at https://github.com/XuandongZhao/WatermarkAttacker","url_abs":"https://arxiv.org/abs/2306.01953v3","url_pdf":"https://arxiv.org/pdf/2306.01953v3.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":"abstracts"},"code_links":[{"paper_slug":"generative-autoencoders-as-watermark","repo_url":"https://github.com/xuandongzhao/watermarkattacker","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"generative-autoencoders-as-watermark","repo_url":"https://github.com/deepvk/metr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-denoising","task_name":"Image Denoising"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2306.01953","atlas_url":"https://app.syntology.ai/?focus=2306.01953","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.01953"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/XuandongZhao/WatermarkAttacker","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/deepvk/metr","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xuandongzhao/watermarkattacker","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"4d47dbd0958277d8","entry":"DiffWMAttacker","repo":"xuandongzhao/watermarkattacker","repo_kind":"official","path":"wmattacker.py","file_url":"https://github.com/xuandongzhao/watermarkattacker/blob/HEAD/wmattacker.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4d47dbd0958277d8"}},{"code_sha256_prefix":"a68246a7e72525c8","entry":"WMAttacker","repo":"xuandongzhao/watermarkattacker","repo_kind":"official","path":"wmattacker.py","file_url":"https://github.com/xuandongzhao/watermarkattacker/blob/HEAD/wmattacker.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a68246a7e72525c8"}},{"code_sha256_prefix":"2f633034edca9832","entry":"compute_psnr","repo":"XuandongZhao/WatermarkAttacker","repo_kind":"official","path":"utils.py","file_url":"https://github.com/XuandongZhao/WatermarkAttacker/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2f633034edca9832"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}