{"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/accelerating-certified-robustness-training","title":"Accelerating Certified Robustness Training via Knowledge Transfer","arxiv_id":"2210.14283","date":"2022-10-25","proceeding":null,"authors":["Pratik Vaishnavi","Kevin Eykholt","Amir Rahmati"],"abstract":"Training deep neural network classifiers that are certifiably robust against adversarial attacks is critical to ensuring the security and reliability of AI-controlled systems. Although numerous state-of-the-art certified training methods have been developed, they are computationally expensive and scale poorly with respect to both dataset and network complexity. Widespread usage of certified training is further hindered by the fact that periodic retraining is necessary to incorporate new data and network improvements. In this paper, we propose Certified Robustness Transfer (CRT), a general-purpose framework for reducing the computational overhead of any certifiably robust training method through knowledge transfer. Given a robust teacher, our framework uses a novel training loss to transfer the teacher's robustness to the student. We provide theoretical and empirical validation of CRT. Our experiments on CIFAR-10 show that CRT speeds up certified robustness training by $8 \\times$ on average across three different architecture generations while achieving comparable robustness to state-of-the-art methods. We also show that CRT can scale to large-scale datasets like ImageNet.","url_abs":"https://arxiv.org/abs/2210.14283v1","url_pdf":"https://arxiv.org/pdf/2210.14283v1.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":"accelerating-certified-robustness-training","repo_url":"https://github.com/ethos-lab/crt-neurips22","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.14283","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.14283"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ethos-lab/crt-neurips22","reach":null}],"summary":{"ran":1,"unverified":4},"by_repo_kind":{"official":{"samples":5,"ran":1,"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":5,"samples":[{"code_sha256_prefix":"7d2be4953e5de042","entry":"Smooth","repo":"ethos-lab/crt-neurips22","repo_kind":"official","path":"helpers/xfer.py","file_url":"https://github.com/ethos-lab/crt-neurips22/blob/HEAD/helpers/xfer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7d2be4953e5de042"}},{"code_sha256_prefix":"4bab6ba943483e3e","entry":"BaseHelper","repo":"ethos-lab/crt-neurips22","repo_kind":"official","path":"helpers/xfer.py","file_url":"https://github.com/ethos-lab/crt-neurips22/blob/HEAD/helpers/xfer.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":"4bab6ba943483e3e"}},{"code_sha256_prefix":"fd0fa56d5e561e97","entry":"XFERHelper","repo":"ethos-lab/crt-neurips22","repo_kind":"official","path":"helpers/xfer.py","file_url":"https://github.com/ethos-lab/crt-neurips22/blob/HEAD/helpers/xfer.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":"fd0fa56d5e561e97"}},{"code_sha256_prefix":"8f4cdfdca525052f","entry":"certify","repo":"ethos-lab/crt-neurips22","repo_kind":"official","path":"helpers/xfer.py","file_url":"https://github.com/ethos-lab/crt-neurips22/blob/HEAD/helpers/xfer.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":"8f4cdfdca525052f"}},{"code_sha256_prefix":"2cdd71d229d75ed1","entry":"save_ckpt","repo":"ethos-lab/crt-neurips22","repo_kind":"official","path":"helpers/xfer.py","file_url":"https://github.com/ethos-lab/crt-neurips22/blob/HEAD/helpers/xfer.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":"2cdd71d229d75ed1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}