{"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":"/code/trades-loss","entry":"trades_loss","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":11,"n_papers_ran":6,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":12,"n_samples_ran":7,"n_samples_fingerprinted":0,"n_places":14,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":5,"ran_fixture":0,"ran":2,"unverified":5},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2505.15174","paper":"/paper/enhancing-certified-robustness-via-block","title":"Enhancing Certified Robustness via Block Reflector Orthogonal Layers and Logit Annealing Loss","date":"2025-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ntuaislab/bronet","path":"bronet/models/margin_layer.py","file_url":"https://github.com/ntuaislab/bronet/blob/HEAD/bronet/models/margin_layer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5d19916d190e1ab2","mcp_get_code":{"code_sha256":"5d19916d190e1ab2"}},{"arxiv_id":"2410.12671","paper":"/paper/new-paradigm-of-adversarial-training-breaking","title":"New Paradigm of Adversarial Training: Breaking Inherent Trade-Off between Accuracy and Robustness via Dummy Classes","date":"2024-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"FlaAI/DUCAT","path":"adv_lib/trades.py","file_url":"https://github.com/FlaAI/DUCAT/blob/HEAD/adv_lib/trades.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"67940ec0772eb65d","mcp_get_code":{"code_sha256":"67940ec0772eb65d"}},{"arxiv_id":"2403.10045","paper":"/paper/towards-adversarially-robust-dataset","title":"Towards Adversarially Robust Dataset Distillation by Curvature Regularization","date":"2024-03-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yumozi/guard","path":"pretrain/pretrain.py","file_url":"https://github.com/yumozi/guard/blob/HEAD/pretrain/pretrain.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"29ca9d1819cac58b","mcp_get_code":{"code_sha256":"29ca9d1819cac58b"}},{"arxiv_id":"2401.12532","paper":"/paper/dafa-distance-aware-fair-adversarial-training","title":"DAFA: Distance-Aware Fair Adversarial Training","date":"2024-01-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rucy74/DAFA","path":"losses.py","file_url":"https://github.com/rucy74/DAFA/blob/HEAD/losses.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"72b23386d15d731a","mcp_get_code":{"code_sha256":"72b23386d15d731a"}},{"arxiv_id":"2006.12135","paper":"/paper/learning-to-generate-noise-for-robustness","title":"Learning to Generate Noise for Multi-Attack Robustness","date":"2020-06-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"divyam3897/MNG_AC","path":"losses.py","file_url":"https://github.com/divyam3897/MNG_AC/blob/HEAD/losses.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d3122446266de554","mcp_get_code":{"code_sha256":"d3122446266de554"}},{"arxiv_id":"2003.00378","paper":"/paper/understanding-the-intrinsic-robustness-of","title":"Understanding the Intrinsic Robustness of Image Distributions using Conditional Generative Models","date":"2020-03-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xiaozhanguva/Intrinsic-Rob","path":"train_classifier/adv_loss.py","file_url":"https://github.com/xiaozhanguva/Intrinsic-Rob/blob/HEAD/train_classifier/adv_loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"92f367701add3745","mcp_get_code":{"code_sha256":"92f367701add3745"}},{"arxiv_id":"2002.03517","paper":"/paper/random-smoothing-might-be-unable-to-certify","title":"Random Smoothing Might be Unable to Certify $\\ell_\\infty$ Robustness for High-Dimensional Images","date":"2020-02-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hongyanz/TRADES-smoothing","path":"code/trades.py","file_url":"https://github.com/hongyanz/TRADES-smoothing/blob/HEAD/code/trades.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"638204e37b37b340","mcp_get_code":{"code_sha256":"638204e37b37b340"}},{"arxiv_id":"1910.09338","paper":"/paper/an-alternative-surrogate-loss-for-pgd-based","title":"An Alternative Surrogate Loss for PGD-based Adversarial Testing","date":"2019-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yaodongyu/TRADES","path":"trades.py","file_url":"https://github.com/yaodongyu/TRADES/blob/HEAD/trades.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0dbf499b0160d7e3","mcp_get_code":{"code_sha256":"0dbf499b0160d7e3"}},{"arxiv_id":"1905.13736","paper":"/paper/unlabeled-data-improves-adversarial","title":"Unlabeled Data Improves Adversarial Robustness","date":"2019-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yguooo/semisup-adv","path":"losses.py","file_url":"https://github.com/yguooo/semisup-adv/blob/HEAD/losses.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b4e250fcdcfa0031","mcp_get_code":{"code_sha256":"b4e250fcdcfa0031"}},{"arxiv_id":"1901.08573","paper":"/paper/theoretically-principled-trade-off-between","title":"Theoretically Principled Trade-off between Robustness and Accuracy","date":"2019-01-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"0dbf499b0160d7e3","mcp_get_code":{"code_sha256":"0dbf499b0160d7e3"}},{"arxiv_id":"1901.08573","paper":"/paper/theoretically-principled-trade-off-between","title":"Theoretically Principled Trade-off between Robustness and Accuracy","date":"2019-01-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TonyYaoMSU/TRADES","path":"TRADES-master/trades.py","file_url":"https://github.com/TonyYaoMSU/TRADES/blob/HEAD/TRADES-master/trades.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4f4e01ae4a9aeecf","mcp_get_code":{"code_sha256":"4f4e01ae4a9aeecf"}},{"arxiv_id":"1901.08573","paper":"/paper/theoretically-principled-trade-off-between","title":"Theoretically Principled Trade-off between Robustness and Accuracy","date":"2019-01-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nutellamok/advrush","path":"advrush/trades.py","file_url":"https://github.com/nutellamok/advrush/blob/HEAD/advrush/trades.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ae05ac36b5660867","mcp_get_code":{"code_sha256":"ae05ac36b5660867"}},{"arxiv_id":"1901.08573","paper":"/paper/theoretically-principled-trade-off-between","title":"Theoretically Principled Trade-off between Robustness and Accuracy","date":"2019-01-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salomonhotegni/MOREL","path":"src/advermorel/losses/trades.py","file_url":"https://github.com/salomonhotegni/MOREL/blob/HEAD/src/advermorel/losses/trades.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e79913f3ab121c59","mcp_get_code":{"code_sha256":"e79913f3ab121c59"}},{"arxiv_id":"aaai_26027","paper":null,"title":"arXiv:aaai_26027","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"UCAS-LCH/Twin-Rep","path":"trades.py","file_url":"https://github.com/UCAS-LCH/Twin-Rep/blob/HEAD/trades.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0dbf499b0160d7e3","mcp_get_code":{"code_sha256":"0dbf499b0160d7e3"}}]}