{"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/robust-representation-learning-via-asymmetric","title":"Enhancing Robust Representation in Adversarial Training: Alignment and Exclusion Criteria","arxiv_id":"2310.03358","date":"2023-10-05","proceeding":null,"authors":["Nuoyan Zhou","Nannan Wang","Decheng Liu","Dawei Zhou","Xinbo Gao"],"abstract":"Deep neural networks are vulnerable to adversarial noise. Adversarial Training (AT) has been demonstrated to be the most effective defense strategy to protect neural networks from being fooled. However, we find AT omits to learning robust features, resulting in poor performance of adversarial robustness. To address this issue, we highlight two criteria of robust representation: (1) Exclusion: \\emph{the feature of examples keeps away from that of other classes}; (2) Alignment: \\emph{the feature of natural and corresponding adversarial examples is close to each other}. These motivate us to propose a generic framework of AT to gain robust representation, by the asymmetric negative contrast and reverse attention. Specifically, we design an asymmetric negative contrast based on predicted probabilities, to push away examples of different classes in the feature space. Moreover, we propose to weight feature by parameters of the linear classifier as the reverse attention, to obtain class-aware feature and pull close the feature of the same class. Empirical evaluations on three benchmark datasets show our methods greatly advance the robustness of AT and achieve state-of-the-art performance.","url_abs":"https://arxiv.org/abs/2310.03358v2","url_pdf":"https://arxiv.org/pdf/2310.03358v2.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":"robust-representation-learning-via-asymmetric","repo_url":"https://github.com/changzhang777/ancra","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"adversarial-attack","task_name":"Adversarial Attack"},{"task_slug":"adversarial-defense","task_name":"Adversarial Defense"},{"task_slug":null,"task_name":"Adversarial Defense against AutoAttack"},{"task_slug":null,"task_name":"Adversarial Defense against PGD"},{"task_slug":"adversarial-robustness","task_name":"Adversarial Robustness"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/adversarial-attack-on-cifar-10","task":"Adversarial Attack","dataset":"CIFAR-10","model":"TRADES-ANCRA/ResNet18","rank_in_archive_order":5,"of":6,"metrics":{"Attack: AutoAttack":"59.70"},"uses_additional_data":false},{"leaderboard":"/sota/adversarial-defense-on-cifar-10","task":"Adversarial Defense","dataset":"CIFAR-10","model":"ResNet18 (TRADES-ANCRA/PGD-40)","rank_in_archive_order":6,"of":8,"metrics":{"Accuracy":"81.70","Attack: AutoAttack":"59.70","Robust Accuracy":"82.96"},"uses_additional_data":false},{"leaderboard":"/sota/adversarial-defense-on-cifar-100","task":"Adversarial Defense","dataset":"CIFAR-100","model":"resnet18","rank_in_archive_order":3,"of":3,"metrics":{"autoattack":"60.10/35.05"},"uses_additional_data":false},{"leaderboard":"/sota/adversarial-robustness-on-cifar-10","task":"Adversarial Robustness","dataset":"CIFAR-10","model":"TRADES-ANCRA/ResNet18","rank_in_archive_order":5,"of":5,"metrics":{"Accuracy":"81.70","Attack: AutoAttack":"59.70"},"uses_additional_data":false},{"leaderboard":"/sota/adversarial-robustness-on-cifar-100","task":"Adversarial Robustness","dataset":"CIFAR-100","model":"ResNet18/MART-ANCRA","rank_in_archive_order":2,"of":2,"metrics":{"AutoAttacked Accuracy":"35.05","Clean Accuracy":"60.10"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"changzhang777/ancra","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"f1b114df038a34551f6e28d04431b2359d72e8e2f9d88d38088532d643211a19","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}