{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/guided-diffusion-model-for-adversarial","title":"Guided Diffusion Model for Adversarial Purification","arxiv_id":"2205.14969","date":"2022-05-30","proceeding":null,"authors":["Jinyi Wang","Zhaoyang Lyu","Dahua Lin","Bo Dai","Hongfei Fu"],"abstract":"With wider application of deep neural networks (DNNs) in various algorithms and frameworks, security threats have become one of the concerns. Adversarial attacks disturb DNN-based image classifiers, in which attackers can intentionally add imperceptible adversarial perturbations on input images to fool the classifiers. In this paper, we propose a novel purification approach, referred to as guided diffusion model for purification (GDMP), to help protect classifiers from adversarial attacks. The core of our approach is to embed purification into the diffusion denoising process of a Denoised Diffusion Probabilistic Model (DDPM), so that its diffusion process could submerge the adversarial perturbations with gradually added Gaussian noises, and both of these noises can be simultaneously removed following a guided denoising process. On our comprehensive experiments across various datasets, the proposed GDMP is shown to reduce the perturbations raised by adversarial attacks to a shallow range, thereby significantly improving the correctness of classification. GDMP improves the robust accuracy by 5%, obtaining 90.1% under PGD attack on the CIFAR10 dataset. Moreover, GDMP achieves 70.94% robustness on the challenging ImageNet dataset.","url_abs":"https://arxiv.org/abs/2205.14969v3","url_pdf":"https://arxiv.org/pdf/2205.14969v3.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":"guided-diffusion-model-for-adversarial","repo_url":"https://github.com/jinyiw/guideddiffusionpur","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"guided-diffusion-model-for-adversarial","repo_url":"https://github.com/adverML/GuidedDiffusionPur","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"adversarial-purification","task_name":"Adversarial Purification"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"model","task_name":"model"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2205.14969","atlas_url":"https://app.syntology.ai/?focus=2205.14969","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2205.14969"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2205.14969\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2205.14969"},"call":"get_concepts_for_paper(arxiv_id=\"2205.14969\")"}],"by_repo":[{"repo":"jinyiw/guideddiffusionpur","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"adverML/GuidedDiffusionPur","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"34f672eef95a2b36fc69f0991776f79d05f633756052e9c273236ce50d72c424","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}