{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/fixing-data-augmentation-to-improve","title":"Fixing Data Augmentation to Improve Adversarial Robustness","arxiv_id":"2103.01946","date":"2021-03-02","proceeding":null,"authors":["Sylvestre-Alvise Rebuffi","Sven Gowal","Dan A. Calian","Florian Stimberg","Olivia Wiles","Timothy Mann"],"abstract":"Adversarial training suffers from robust overfitting, a phenomenon where the robust test accuracy starts to decrease during training. In this paper, we focus on both heuristics-driven and data-driven augmentations as a means to reduce robust overfitting. First, we demonstrate that, contrary to previous findings, when combined with model weight averaging, data augmentation can significantly boost robust accuracy. Second, we explore how state-of-the-art generative models can be leveraged to artificially increase the size of the training set and further improve adversarial robustness. Finally, we evaluate our approach on CIFAR-10 against $\\ell_\\infty$ and $\\ell_2$ norm-bounded perturbations of size $\\epsilon = 8/255$ and $\\epsilon = 128/255$, respectively. We show large absolute improvements of +7.06% and +5.88% in robust accuracy compared to previous state-of-the-art methods. In particular, against $\\ell_\\infty$ norm-bounded perturbations of size $\\epsilon = 8/255$, our model reaches 64.20% robust accuracy without using any external data, beating most prior works that use external data.","url_abs":"https://arxiv.org/abs/2103.01946v2","url_pdf":"https://arxiv.org/pdf/2103.01946v2.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":"fixing-data-augmentation-to-improve","repo_url":"https://github.com/deepmind/deepmind-research","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"fixing-data-augmentation-to-improve","repo_url":"https://github.com/BjoernNieth/LS-Dataset-pruning-in-AT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"fixing-data-augmentation-to-improve","repo_url":"https://github.com/imrahulr/adversarial_robustness_pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"fixing-data-augmentation-to-improve","repo_url":"https://github.com/imrahulr/hat","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"fixing-data-augmentation-to-improve","repo_url":"https://github.com/p2333/score","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"fixing-data-augmentation-to-improve","repo_url":"https://github.com/wzekai99/dm-improves-at","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"fixing-data-augmentation-to-improve","repo_url":"https://github.com/yuyuwu5/ADR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"adversarial-robustness","task_name":"Adversarial Robustness"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2103.01946","atlas_url":"https://app.syntology.ai/?focus=2103.01946","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2103.01946"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2103.01946\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2103.01946"},"call":"get_concepts_for_paper(arxiv_id=\"2103.01946\")"}],"by_repo":[{"repo":"deepmind/deepmind-research","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":4,"harvested_for":["2006.12982","2101.08692","2103.03206","2105.14039"],"harvested_for_calls":[{"arxiv_id":"2006.12982","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2006.12982"},"call":"get_harvested_code_for_paper(arxiv_id=\"2006.12982\")"},{"arxiv_id":"2101.08692","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2101.08692"},"call":"get_harvested_code_for_paper(arxiv_id=\"2101.08692\")"},{"arxiv_id":"2103.03206","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2103.03206"},"call":"get_harvested_code_for_paper(arxiv_id=\"2103.03206\")"},{"arxiv_id":"2105.14039","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2105.14039"},"call":"get_harvested_code_for_paper(arxiv_id=\"2105.14039\")"}]},{"repo":"BjoernNieth/LS-Dataset-pruning-in-AT","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2406.13283"],"harvested_for_calls":[{"arxiv_id":"2406.13283","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2406.13283"},"call":"get_harvested_code_for_paper(arxiv_id=\"2406.13283\")"}]},{"repo":"imrahulr/adversarial_robustness_pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2110.09468"],"harvested_for_calls":[{"arxiv_id":"2110.09468","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2110.09468"},"call":"get_harvested_code_for_paper(arxiv_id=\"2110.09468\")"}]},{"repo":"imrahulr/hat","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"p2333/score","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2202.10103"],"harvested_for_calls":[{"arxiv_id":"2202.10103","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2202.10103"},"call":"get_harvested_code_for_paper(arxiv_id=\"2202.10103\")"}]},{"repo":"wzekai99/dm-improves-at","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2606.02267"],"harvested_for_calls":[{"arxiv_id":"2606.02267","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2606.02267"},"call":"get_harvested_code_for_paper(arxiv_id=\"2606.02267\")"}]},{"repo":"yuyuwu5/ADR","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2305.12118"],"harvested_for_calls":[{"arxiv_id":"2305.12118","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2305.12118"},"call":"get_harvested_code_for_paper(arxiv_id=\"2305.12118\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"f175a29ca2976e32fa8600447fb99f4f9d52fe98fa520863fe6cf8e54fc1507e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}