{"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/large-scale-dataset-pruning-in-adversarial","title":"Large-Scale Dataset Pruning in Adversarial Training through Data Importance Extrapolation","arxiv_id":"2406.13283","date":"2024-06-19","proceeding":null,"authors":["Björn Nieth","Thomas Altstidl","Leo Schwinn","Björn Eskofier"],"abstract":"Their vulnerability to small, imperceptible attacks limits the adoption of deep learning models to real-world systems. Adversarial training has proven to be one of the most promising strategies against these attacks, at the expense of a substantial increase in training time. With the ongoing trend of integrating large-scale synthetic data this is only expected to increase even further. Thus, the need for data-centric approaches that reduce the number of training samples while maintaining accuracy and robustness arises. While data pruning and active learning are prominent research topics in deep learning, they are as of now largely unexplored in the adversarial training literature. We address this gap and propose a new data pruning strategy based on extrapolating data importance scores from a small set of data to a larger set. In an empirical evaluation, we demonstrate that extrapolation-based pruning can efficiently reduce dataset size while maintaining robustness.","url_abs":"https://arxiv.org/abs/2406.13283v2","url_pdf":"https://arxiv.org/pdf/2406.13283v2.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":"large-scale-dataset-pruning-in-adversarial","repo_url":"https://github.com/BjoernNieth/LS-Dataset-pruning-in-AT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"active-learning","task_name":"Active Learning"},{"task_slug":"deep-learning","task_name":"Deep Learning"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"},{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.13283","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13283"}},"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/BjoernNieth/LS-Dataset-pruning-in-AT","reach":{"status":"ok"}}],"summary":{"ran":7,"unverified":2},"by_repo_kind":{"official":{"samples":9,"ran":7,"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":9,"samples":[{"code_sha256_prefix":"6d57c3097e379953","entry":"calc_l2distsq","repo":"BjoernNieth/LS-Dataset-pruning-in-AT","repo_kind":"official","path":"core/attacks/utils.py","file_url":"https://github.com/BjoernNieth/LS-Dataset-pruning-in-AT/blob/HEAD/core/attacks/utils.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6d57c3097e379953"}},{"code_sha256_prefix":"8a6e2e06ca96fb3c","entry":"perturb_deepfool","repo":"BjoernNieth/LS-Dataset-pruning-in-AT","repo_kind":"official","path":"core/attacks/deepfool.py","file_url":"https://github.com/BjoernNieth/LS-Dataset-pruning-in-AT/blob/HEAD/core/attacks/deepfool.py","link_basis":"plan_row","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":"8a6e2e06ca96fb3c"}},{"code_sha256_prefix":"a99efdab28da25d8","entry":"preact_resnet","repo":"BjoernNieth/LS-Dataset-pruning-in-AT","repo_kind":"official","path":"core/models/preact_resnet.py","file_url":"https://github.com/BjoernNieth/LS-Dataset-pruning-in-AT/blob/HEAD/core/models/preact_resnet.py","link_basis":"plan_row","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":"a99efdab28da25d8"}},{"code_sha256_prefix":"096e065144e00e11","entry":"replicate_input","repo":"BjoernNieth/LS-Dataset-pruning-in-AT","repo_kind":"official","path":"core/attacks/utils.py","file_url":"https://github.com/BjoernNieth/LS-Dataset-pruning-in-AT/blob/HEAD/core/attacks/utils.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"096e065144e00e11"}},{"code_sha256_prefix":"706e45721616b050","entry":"replicate_input_withgrad","repo":"BjoernNieth/LS-Dataset-pruning-in-AT","repo_kind":"official","path":"core/attacks/utils.py","file_url":"https://github.com/BjoernNieth/LS-Dataset-pruning-in-AT/blob/HEAD/core/attacks/utils.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"706e45721616b050"}},{"code_sha256_prefix":"faacf3bc6eae58ae","entry":"resnet","repo":"BjoernNieth/LS-Dataset-pruning-in-AT","repo_kind":"official","path":"core/models/resnet.py","file_url":"https://github.com/BjoernNieth/LS-Dataset-pruning-in-AT/blob/HEAD/core/models/resnet.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":"faacf3bc6eae58ae"}},{"code_sha256_prefix":"b83aa0df4382b430","entry":"ti_preact_resnet","repo":"BjoernNieth/LS-Dataset-pruning-in-AT","repo_kind":"official","path":"core/models/ti_preact_resnet.py","file_url":"https://github.com/BjoernNieth/LS-Dataset-pruning-in-AT/blob/HEAD/core/models/ti_preact_resnet.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":"b83aa0df4382b430"}},{"code_sha256_prefix":"ec5326fd666c5823","entry":"perturb_iterative","repo":"BjoernNieth/LS-Dataset-pruning-in-AT","repo_kind":"official","path":"core/attacks/pgd.py","file_url":"https://github.com/BjoernNieth/LS-Dataset-pruning-in-AT/blob/HEAD/core/attacks/pgd.py","link_basis":"plan_row","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":"ec5326fd666c5823"}},{"code_sha256_prefix":"6dfdd3eb06e12783","entry":"preact_resnetwithswish","repo":"BjoernNieth/LS-Dataset-pruning-in-AT","repo_kind":"official","path":"core/models/preact_resnetwithswish.py","file_url":"https://github.com/BjoernNieth/LS-Dataset-pruning-in-AT/blob/HEAD/core/models/preact_resnetwithswish.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":"6dfdd3eb06e12783"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}