{"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/diffusion-based-adversarial-sample-generation-1","title":"Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability","arxiv_id":"2305.16494","date":"2023-05-25","proceeding":"NeurIPS 2023 11","authors":["Haotian Xue","Alexandre Araujo","Bin Hu","Yongxin Chen"],"abstract":"Neural networks are known to be susceptible to adversarial samples: small variations of natural examples crafted to deliberately mislead the models. While they can be easily generated using gradient-based techniques in digital and physical scenarios, they often differ greatly from the actual data distribution of natural images, resulting in a trade-off between strength and stealthiness. In this paper, we propose a novel framework dubbed Diffusion-Based Projected Gradient Descent (Diff-PGD) for generating realistic adversarial samples. By exploiting a gradient guided by a diffusion model, Diff-PGD ensures that adversarial samples remain close to the original data distribution while maintaining their effectiveness. Moreover, our framework can be easily customized for specific tasks such as digital attacks, physical-world attacks, and style-based attacks. Compared with existing methods for generating natural-style adversarial samples, our framework enables the separation of optimizing adversarial loss from other surrogate losses (e.g., content/smoothness/style loss), making it more stable and controllable. Finally, we demonstrate that the samples generated using Diff-PGD have better transferability and anti-purification power than traditional gradient-based methods. Code will be released in https://github.com/xavihart/Diff-PGD","url_abs":"https://arxiv.org/abs/2305.16494v3","url_pdf":"https://arxiv.org/pdf/2305.16494v3.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":"diffusion-based-adversarial-sample-generation-1","repo_url":"https://github.com/xavihart/diff-pgd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.16494","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.16494"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/xavihart/Diff-PGD","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xavihart/diff-pgd","reach":null}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"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":3,"samples":[{"code_sha256_prefix":"49d47f0975f00d99","entry":"Denoised_Classifier","repo":"xavihart/diff-pgd","repo_kind":"official","path":"code/attack_v1.py","file_url":"https://github.com/xavihart/diff-pgd/blob/HEAD/code/attack_v1.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"49d47f0975f00d99"}},{"code_sha256_prefix":"bc9a1b961ae57bbc","entry":"generate_x_adv_denoised_v2","repo":"xavihart/Diff-PGD","repo_kind":"official","path":"code/attack_global.py","file_url":"https://github.com/xavihart/Diff-PGD/blob/HEAD/code/attack_global.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bc9a1b961ae57bbc"}},{"code_sha256_prefix":"5a9951fec2e97867","entry":"style_transfer","repo":"xavihart/Diff-PGD","repo_kind":"official","path":"code/attack_style.py","file_url":"https://github.com/xavihart/Diff-PGD/blob/HEAD/code/attack_style.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5a9951fec2e97867"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}