{"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/defending-black-box-skeleton-based-human","title":"Defending Black-box Skeleton-based Human Activity Classifiers","arxiv_id":"2203.04713","date":"2022-03-09","proceeding":null,"authors":["He Wang","Yunfeng Diao","Zichang Tan","Guodong Guo"],"abstract":"Skeletal motions have been heavily replied upon for human activity recognition (HAR). Recently, a universal vulnerability of skeleton-based HAR has been identified across a variety of classifiers and data, calling for mitigation. To this end, we propose the first black-box defense method for skeleton-based HAR to our best knowledge. Our method is featured by full Bayesian treatments of the clean data, the adversaries and the classifier, leading to (1) a new Bayesian Energy-based formulation of robust discriminative classifiers, (2) a new adversary sampling scheme based on natural motion manifolds, and (3) a new post-train Bayesian strategy for black-box defense. We name our framework Bayesian Energy-based Adversarial Training or BEAT. BEAT is straightforward but elegant, which turns vulnerable black-box classifiers into robust ones without sacrificing accuracy. It demonstrates surprising and universal effectiveness across a wide range of skeletal HAR classifiers and datasets, under various attacks. Code is available at https://github.com/realcrane/RobustActionRecogniser.","url_abs":"https://arxiv.org/abs/2203.04713v6","url_pdf":"https://arxiv.org/pdf/2203.04713v6.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":"defending-black-box-skeleton-based-human","repo_url":"https://github.com/realcrane/robustactionrecogniser","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"defending-black-box-skeleton-based-human","repo_url":"https://github.com/realcrane/Defending-Black-box-Skeleton-based-Human-Activity-Classifiers","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"activity-recognition","task_name":"Activity Recognition"},{"task_slug":"human-activity-recognition","task_name":"Human Activity Recognition"},{"task_slug":"time-series","task_name":"Time Series Analysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.04713","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}