{"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/feature-partition-aggregation-a-fast","title":"Provable Robustness Against a Union of $\\ell_0$ Adversarial Attacks","arxiv_id":"2302.11628","date":"2023-02-22","proceeding":null,"authors":["Zayd Hammoudeh","Daniel Lowd"],"abstract":"Sparse or $\\ell_0$ adversarial attacks arbitrarily perturb an unknown subset of the features. $\\ell_0$ robustness analysis is particularly well-suited for heterogeneous (tabular) data where features have different types or scales. State-of-the-art $\\ell_0$ certified defenses are based on randomized smoothing and apply to evasion attacks only. This paper proposes feature partition aggregation (FPA) -- a certified defense against the union of $\\ell_0$ evasion, backdoor, and poisoning attacks. FPA generates its stronger robustness guarantees via an ensemble whose submodels are trained on disjoint feature sets. Compared to state-of-the-art $\\ell_0$ defenses, FPA is up to 3,000${\\times}$ faster and provides larger median robustness guarantees (e.g., median certificates of 13 pixels over 10 for CIFAR10, 12 pixels over 10 for MNIST, 4 features over 1 for Weather, and 3 features over 1 for Ames), meaning FPA provides the additional dimensions of robustness essentially for free.","url_abs":"https://arxiv.org/abs/2302.11628v4","url_pdf":"https://arxiv.org/pdf/2302.11628v4.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":"feature-partition-aggregation-a-fast","repo_url":"https://github.com/zaydh/feature-partition","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"feature-partition-aggregation-a-fast","repo_url":"https://github.com/zaydh/target_identification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"randomized-smoothing","method_name":"Randomized Smoothing"},{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}