{"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/raising-the-cost-of-malicious-ai-powered","title":"Raising the Cost of Malicious AI-Powered Image Editing","arxiv_id":"2302.06588","date":"2023-02-13","proceeding":null,"authors":["Hadi Salman","Alaa Khaddaj","Guillaume Leclerc","Andrew Ilyas","Aleksander Madry"],"abstract":"We present an approach to mitigating the risks of malicious image editing posed by large diffusion models. The key idea is to immunize images so as to make them resistant to manipulation by these models. This immunization relies on injection of imperceptible adversarial perturbations designed to disrupt the operation of the targeted diffusion models, forcing them to generate unrealistic images. We provide two methods for crafting such perturbations, and then demonstrate their efficacy. Finally, we discuss a policy component necessary to make our approach fully effective and practical -- one that involves the organizations developing diffusion models, rather than individual users, to implement (and support) the immunization process.","url_abs":"https://arxiv.org/abs/2302.06588v1","url_pdf":"https://arxiv.org/pdf/2302.06588v1.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":"raising-the-cost-of-malicious-ai-powered","repo_url":"https://github.com/madrylab/photoguard","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2302.06588","atlas_url":"https://app.syntology.ai/?focus=2302.06588","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.06588"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/madrylab/photoguard","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":"d2ed2aee909f3cb0","entry":"preprocess","repo":"madrylab/photoguard","repo_kind":"official","path":"demo/utils.py","file_url":"https://github.com/madrylab/photoguard/blob/HEAD/demo/utils.py","link_basis":"harvester_set","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":"d2ed2aee909f3cb0"}},{"code_sha256_prefix":"2c7bfa328b02b933","entry":"recover_image","repo":"madrylab/photoguard","repo_kind":"official","path":"demo/utils.py","file_url":"https://github.com/madrylab/photoguard/blob/HEAD/demo/utils.py","link_basis":"harvester_set","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":"2c7bfa328b02b933"}},{"code_sha256_prefix":"b9c0f2d222ed2c14","entry":"resize_and_crop","repo":"madrylab/photoguard","repo_kind":"official","path":"demo/utils.py","file_url":"https://github.com/madrylab/photoguard/blob/HEAD/demo/utils.py","link_basis":"harvester_set","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":"b9c0f2d222ed2c14"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}