{"url":"/task/adversarial-purification","name":"Adversarial Purification","slug":"adversarial-purification","description_markdown":"A class of adversarial defense methods that remove adversarial perturbations using a generative model.","categories":[{"name":"Adversarial","url":"/area/adversarial"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":65,"papers_with_code":27,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":0,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[{"url":"/task/adversarial-defense","name":"Adversarial Defense"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":27,"of":27,"tagged_in_all":65,"items":[{"url":"/paper/guided-diffusion-model-for-adversarial","title":"Guided Diffusion Model for Adversarial Purification","date":"2022-05-30","arxiv_id":"2205.14969","repositories_listed":2,"syntology":null},{"url":"/paper/diffusion-models-for-adversarial-purification","title":"Diffusion Models for Adversarial Purification","date":"2022-05-16","arxiv_id":"2205.07460","repositories_listed":2,"syntology":{"n":23,"n_ran":11,"n_unverified":12,"n_pointer_only":5}},{"url":"/paper/flowpure-continuous-normalizing-flows-for","title":"FlowPure: Continuous Normalizing Flows for Adversarial Purification","date":"2025-05-19","arxiv_id":"2505.13280","repositories_listed":1,"syntology":null},{"url":"/paper/lisard-learning-image-similarity-to-defend","title":"LISArD: Learning Image Similarity to Defend Against Gray-box Adversarial Attacks","date":"2025-02-27","arxiv_id":"2502.20562","repositories_listed":1,"syntology":null},{"url":"/paper/videopure-diffusion-based-adversarial","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","date":"2025-01-25","arxiv_id":"2501.14999","repositories_listed":1,"syntology":null},{"url":"/paper/pre-trained-multiple-latent-variable","title":"Pre-trained Multiple Latent Variable Generative Models are good defenders against Adversarial Attacks","date":"2024-12-04","arxiv_id":"2412.03453","repositories_listed":1,"syntology":null},{"url":"/paper/random-sampling-for-diffusion-based","title":"Random Sampling for Diffusion-based Adversarial Purification","date":"2024-11-28","arxiv_id":"2411.18956","repositories_listed":1,"syntology":null},{"url":"/paper/high-frequency-anti-dreambooth-robust-defense","title":"High-Frequency Anti-DreamBooth: Robust Defense against Personalized Image Synthesis","date":"2024-09-12","arxiv_id":"2409.08167","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":6}},{"url":"/paper/detecting-and-defending-against-adversarial","title":"Detecting and Defending Against Adversarial Attacks on Automatic Speech Recognition via Diffusion Models","date":"2024-09-12","arxiv_id":"2409.07936","repositories_listed":1,"syntology":null},{"url":"/paper/2408-01541","title":"Guardians of Image Quality: Benchmarking Defenses Against Adversarial Attacks on Image Quality Metrics","date":"2024-08-02","arxiv_id":"2408.01541","repositories_listed":1,"syntology":null},{"url":"/paper/diffusion-based-adversarial-purification-for-2","title":"Diffusion-based Adversarial Purification for Intrusion Detection","date":"2024-06-25","arxiv_id":"2406.17606","repositories_listed":1,"syntology":null},{"url":"/paper/zeropur-succinct-training-free-adversarial","title":"ZeroPur: Succinct Training-Free Adversarial Purification","date":"2024-06-05","arxiv_id":"2406.03143","repositories_listed":1,"syntology":{"n":13,"n_ran":7,"n_unverified":6,"n_pointer_only":13}},{"url":"/paper/robust-overfitting-does-matter-test-time","title":"Robust Overfitting Does Matter: Test-Time Adversarial Purification With FGSM","date":"2024-03-18","arxiv_id":"2403.11448","repositories_listed":1,"syntology":null},{"url":"/paper/pcld-point-cloud-layerwise-diffusion-for","title":"PCLD: Point Cloud Layerwise Diffusion for Adversarial Purification","date":"2024-03-11","arxiv_id":"2403.06698","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-training-on-purification-atop","title":"Adversarial Training on Purification (AToP): Advancing Both Robustness and Generalization","date":"2024-01-29","arxiv_id":"2401.16352","repositories_listed":1,"syntology":{"n":18,"n_ran":14,"n_unverified":4,"n_pointer_only":18}},{"url":"/paper/malpurifier-enhancing-android-malware","title":"MalPurifier: Enhancing Android Malware Detection with Adversarial Purification against Evasion Attacks","date":"2023-12-11","arxiv_id":"2312.06423","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-purification-of-information","title":"Adversarial Purification of Information Masking","date":"2023-11-26","arxiv_id":"2311.15339","repositories_listed":1,"syntology":null},{"url":"/paper/diffusion-models-meet-image-counter-forensics","title":"Diffusion models meet image counter-forensics","date":"2023-11-22","arxiv_id":"2311.13629","repositories_listed":1,"syntology":null},{"url":"/paper/diffattack-evasion-attacks-against-diffusion-1","title":"DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification","date":"2023-10-27","arxiv_id":"2311.16124","repositories_listed":1,"syntology":{"n":24,"n_ran":18,"n_unverified":6,"n_pointer_only":21}},{"url":"/paper/language-guided-adversarial-purification","title":"Language Guided Adversarial Purification","date":"2023-09-19","arxiv_id":"2309.10348","repositories_listed":1,"syntology":null},{"url":"/paper/diffsmooth-certifiably-robust-learning-via","title":"DiffSmooth: Certifiably Robust Learning via Diffusion Models and Local Smoothing","date":"2023-08-28","arxiv_id":"2308.14333","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":6}},{"url":"/paper/universal-adversarial-defense-in-remote","title":"Universal Adversarial Defense in Remote Sensing Based on Pre-trained Denoising Diffusion Models","date":"2023-07-31","arxiv_id":"2307.16865","repositories_listed":1,"syntology":null},{"url":"/paper/carso-counter-adversarial-recall-of-synthetic","title":"Carefully Blending Adversarial Training, Purification, and Aggregation Improves Adversarial Robustness","date":"2023-05-25","arxiv_id":"2306.06081","repositories_listed":1,"syntology":null},{"url":"/paper/robust-evaluation-of-diffusion-based","title":"Robust Evaluation of Diffusion-Based Adversarial Purification","date":"2023-03-16","arxiv_id":"2303.09051","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/defending-against-adversarial-audio-via","title":"Defending against Adversarial Audio via Diffusion Model","date":"2023-03-02","arxiv_id":"2303.01507","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-purification-with-score-based","title":"Adversarial purification with Score-based generative models","date":"2021-06-11","arxiv_id":"2106.06041","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/stochastic-security-adversarial-defense-using","title":"Stochastic Security: Adversarial Defense Using Long-Run Dynamics of Energy-Based Models","date":"2020-05-27","arxiv_id":"2005.13525","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}}],"syntology_records":9,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}