{"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":"/task/adversarial-robustness/papers/7","list_of":"/task/adversarial-robustness","task":"Adversarial Robustness","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":7,"pages_in_order":18,"rows_per_page":100,"rows":[601,700],"of":1746,"counts":{"archive_papers_tagged":1746,"with_a_code_link":788,"where_syntology_ran_a_sample":261,"not_listed_spam_title":0,"listed":1746,"listed_where_code_ran":261,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":205,"every_run_a_failure_of_syntologys_instrument":56,"listed_with_a_run_with_no_instrument_failure":205,"listed_every_run_a_failure_of_syntologys_instrument":56,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/adversarial-robustness","prev":"/task/adversarial-robustness/papers/6","next":"/task/adversarial-robustness/papers/8","papers":[{"url":"/paper/probabilistic-margins-for-instance","slug":"probabilistic-margins-for-instance","title":"Probabilistic Margins for Instance Reweighting in Adversarial Training","date":"2021-06-15","arxiv_id":"2106.07904","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-robustness-via-fisher-rao","slug":"adversarial-robustness-via-fisher-rao","title":"Adversarial Robustness via Fisher-Rao Regularization","date":"2021-06-12","arxiv_id":"2106.06685","repositories_listed":1,"syntology":null},{"url":"/paper/cartl-cooperative-adversarially-robust","slug":"cartl-cooperative-adversarially-robust","title":"CARTL: Cooperative Adversarially-Robust Transfer Learning","date":"2021-06-12","arxiv_id":"2106.06667","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cartl-cooperative-adversarially-robust#ran","syntology_url":"https://syntology.ai/paper/2106.06667","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06667"}},"official":{"repos":["NISP-official/CARTL"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/adversarial-robustness-through-the-lens-of","slug":"adversarial-robustness-through-the-lens-of","title":"CausalAdv: Adversarial Robustness through the Lens of Causality","date":"2021-06-11","arxiv_id":"2106.06196","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-attack-and-defense-in-deep","slug":"adversarial-attack-and-defense-in-deep","title":"Adversarial Attack and Defense in Deep Ranking","date":"2021-06-07","arxiv_id":"2106.03614","repositories_listed":1,"syntology":null},{"url":"/paper/k-mixup-regularization-for-deep-learning-via","slug":"k-mixup-regularization-for-deep-learning-via","title":"k-Mixup Regularization for Deep Learning via Optimal Transport","date":"2021-06-05","arxiv_id":"2106.02933","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/k-mixup-regularization-for-deep-learning-via#ran","syntology_url":"https://syntology.ai/paper/2106.02933","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.02933"}},"official":{"repos":["anminggu/kmixup-cifar10"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/revisiting-hilbert-schmidt-information","slug":"revisiting-hilbert-schmidt-information","title":"Revisiting Hilbert-Schmidt Information Bottleneck for Adversarial Robustness","date":"2021-06-04","arxiv_id":"2106.02734","repositories_listed":1,"syntology":{"n":16,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":9,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/revisiting-hilbert-schmidt-information#ran","syntology_url":"https://syntology.ai/paper/2106.02734","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.02734"}},"official":{"repos":["neu-spiral/hbar"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/robust-learning-via-persistency-of-excitation","slug":"robust-learning-via-persistency-of-excitation","title":"Improving Neural Network Robustness via Persistency of Excitation","date":"2021-06-03","arxiv_id":"2106.02078","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/robust-learning-via-persistency-of-excitation#ran","syntology_url":"https://syntology.ai/paper/2106.02078","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.02078"}},"official":{"repos":["kaustubhsridhar/PoE-robustness"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/noilin-do-noisy-labels-always-hurt","slug":"noilin-do-noisy-labels-always-hurt","title":"NoiLIn: Improving Adversarial Training and Correcting Stereotype of Noisy Labels","date":"2021-05-31","arxiv_id":"2105.14676","repositories_listed":1,"syntology":null},{"url":"/paper/the-sobolev-regularization-effect-of","slug":"the-sobolev-regularization-effect-of","title":"On Linear Stability of SGD and Input-Smoothness of Neural Networks","date":"2021-05-27","arxiv_id":"2105.13462","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/the-sobolev-regularization-effect-of#ran","syntology_url":"https://syntology.ai/paper/2105.13462","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.13462"}},"official":{"repos":["ChaoMa93/Sobolev-Reg-of-SGD"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/adversarial-robustness-against-multiple-l-p","slug":"adversarial-robustness-against-multiple-l-p","title":"Adversarial Robustness against Multiple and Single $l_p$-Threat Models via Quick Fine-Tuning of Robust Classifiers","date":"2021-05-26","arxiv_id":"2105.12508","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adversarial-robustness-against-multiple-l-p#ran","syntology_url":"https://syntology.ai/paper/2105.12508","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.12508"}},"official":{"repos":["fra31/robust-finetuning"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/skew-orthogonal-convolutions","slug":"skew-orthogonal-convolutions","title":"Skew Orthogonal Convolutions","date":"2021-05-24","arxiv_id":"2105.11417","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":0,"n_instrument":8,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/skew-orthogonal-convolutions#ran","syntology_url":"https://syntology.ai/paper/2105.11417","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.11417"}},"official":{"repos":["singlasahil14/SOC"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/an-orthogonal-classifier-for-improving-the","slug":"an-orthogonal-classifier-for-improving-the","title":"An Orthogonal Classifier for Improving the Adversarial Robustness of Neural Networks","date":"2021-05-19","arxiv_id":"2105.09109","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/an-orthogonal-classifier-for-improving-the#ran","syntology_url":"https://syntology.ai/paper/2105.09109","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.09109"}},"official":{"repos":["MTandHJ/roboc"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/theoretical-study-of-random-noise-defense","slug":"theoretical-study-of-random-noise-defense","title":"Random Noise Defense Against Query-Based Black-Box Attacks","date":"2021-04-23","arxiv_id":"2104.11470","repositories_listed":1,"syntology":null},{"url":"/paper/towards-adversarial-patch-analysis-and","slug":"towards-adversarial-patch-analysis-and","title":"Towards Adversarial Patch Analysis and Certified Defense against Crowd Counting","date":"2021-04-22","arxiv_id":"2104.10868","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-faithfulness-measurements-for-model","slug":"on-the-faithfulness-measurements-for-model","title":"On the Sensitivity and Stability of Model Interpretations in NLP","date":"2021-04-18","arxiv_id":"2104.08782","repositories_listed":1,"syntology":null},{"url":"/paper/does-language-help-generalization-in-vision","slug":"does-language-help-generalization-in-vision","title":"Does language help generalization in vision models?","date":"2021-04-16","arxiv_id":"2104.08313","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/does-language-help-generalization-in-vision#ran","syntology_url":"https://syntology.ai/paper/2104.08313","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08313"}},"official":{"repos":["bdvllrs/generalization-vision"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/orthogonalizing-convolutional-layers-with-the-1","slug":"orthogonalizing-convolutional-layers-with-the-1","title":"Orthogonalizing Convolutional Layers with the Cayley Transform","date":"2021-04-14","arxiv_id":"2104.07167","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/orthogonalizing-convolutional-layers-with-the-1#ran","syntology_url":"https://syntology.ai/paper/2104.07167","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.07167"}},"official":{"repos":["locuslab/orthogonal-convolutions"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/adversarial-robustness-guarantees-for","slug":"adversarial-robustness-guarantees-for","title":"Adversarial Robustness Guarantees for Gaussian Processes","date":"2021-04-07","arxiv_id":"2104.03180","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-robustness-under-long-tailed","slug":"adversarial-robustness-under-long-tailed","title":"Adversarial Robustness under Long-Tailed Distribution","date":"2021-04-06","arxiv_id":"2104.02703","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/adversarial-robustness-under-long-tailed#ran","syntology_url":"https://syntology.ai/paper/2104.02703","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.02703"}},"official":{"repos":["wutong16/Adversarial_Long-Tail"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/what-causes-optical-flow-networks-to-be","slug":"what-causes-optical-flow-networks-to-be","title":"Towards Understanding Adversarial Robustness of Optical Flow Networks","date":"2021-03-30","arxiv_id":"2103.16255","repositories_listed":1,"syntology":null},{"url":"/paper/2103-15670","slug":"2103-15670","title":"On the Adversarial Robustness of Vision Transformers","date":"2021-03-29","arxiv_id":"2103.15670","repositories_listed":1,"syntology":null},{"url":"/paper/drop-bottleneck-learning-discrete-compressed-1","slug":"drop-bottleneck-learning-discrete-compressed-1","title":"Drop-Bottleneck: Learning Discrete Compressed Representation for Noise-Robust Exploration","date":"2021-03-23","arxiv_id":"2103.12300","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/drop-bottleneck-learning-discrete-compressed-1#ran","syntology_url":"https://syntology.ai/paper/2103.12300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.12300"}},"official":{"repos":["jaekyeom/drop-bottleneck"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/interpretable-deep-learning-interpretations","slug":"interpretable-deep-learning-interpretations","title":"Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond","date":"2021-03-19","arxiv_id":"2103.10689","repositories_listed":1,"syntology":null},{"url":"/paper/generating-adversarial-computer-programs-1","slug":"generating-adversarial-computer-programs-1","title":"Generating Adversarial Computer Programs using Optimized Obfuscations","date":"2021-03-18","arxiv_id":"2103.11882","repositories_listed":1,"syntology":null},{"url":"/paper/constant-random-perturbations-provide","slug":"constant-random-perturbations-provide","title":"Constant Random Perturbations Provide Adversarial Robustness with Minimal Effect on Accuracy","date":"2021-03-15","arxiv_id":"2103.08265","repositories_listed":1,"syntology":null},{"url":"/paper/game-theoretic-understanding-of-adversarially","slug":"game-theoretic-understanding-of-adversarially","title":"A Unified Game-Theoretic Interpretation of Adversarial Robustness","date":"2021-03-12","arxiv_id":"2103.07364","repositories_listed":1,"syntology":null},{"url":"/paper/improving-adversarial-robustness-via-channel-1","slug":"improving-adversarial-robustness-via-channel-1","title":"Improving Adversarial Robustness via Channel-wise Activation Suppressing","date":"2021-03-11","arxiv_id":"2103.08307","repositories_listed":1,"syntology":null},{"url":"/paper/consistency-regularization-for-adversarial","slug":"consistency-regularization-for-adversarial","title":"Consistency Regularization for Adversarial Robustness","date":"2021-03-08","arxiv_id":"2103.04623","repositories_listed":1,"syntology":null},{"url":"/paper/shift-invariance-can-reduce-adversarial","slug":"shift-invariance-can-reduce-adversarial","title":"Shift Invariance Can Reduce Adversarial Robustness","date":"2021-03-03","arxiv_id":"2103.02695","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/shift-invariance-can-reduce-adversarial#ran","syntology_url":"https://syntology.ai/paper/2103.02695","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.02695"}},"official":{"repos":["SongweiGe/shift-invariance-adv-robustness"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/explaining-adversarial-vulnerability-with-a","slug":"explaining-adversarial-vulnerability-with-a","title":"Explaining Adversarial Vulnerability with a Data Sparsity Hypothesis","date":"2021-03-01","arxiv_id":"2103.00778","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-robustness-with-non-uniform","slug":"adversarial-robustness-with-non-uniform","title":"Adversarial Robustness with Non-uniform Perturbations","date":"2021-02-24","arxiv_id":"2102.12002","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adversarial-robustness-with-non-uniform#ran","syntology_url":"https://syntology.ai/paper/2102.12002","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.12002"}},"official":{"repos":["amazon-research/adversarial-robustness-with-nonuniform-perturbations"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multiplicative-reweighting-for-robust-neural","slug":"multiplicative-reweighting-for-robust-neural","title":"Multiplicative Reweighting for Robust Neural Network Optimization","date":"2021-02-24","arxiv_id":"2102.12192","repositories_listed":1,"syntology":null},{"url":"/paper/on-fast-adversarial-robustness-adaptation-in-1","slug":"on-fast-adversarial-robustness-adaptation-in-1","title":"On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning","date":"2021-02-20","arxiv_id":"2102.10454","repositories_listed":1,"syntology":null},{"url":"/paper/a-pac-bayes-analysis-of-adversarial","slug":"a-pac-bayes-analysis-of-adversarial","title":"A PAC-Bayes Analysis of Adversarial Robustness","date":"2021-02-19","arxiv_id":"2102.11069","repositories_listed":1,"syntology":null},{"url":"/paper/center-smoothing-for-certifiably-robust","slug":"center-smoothing-for-certifiably-robust","title":"Center Smoothing: Certified Robustness for Networks with Structured Outputs","date":"2021-02-19","arxiv_id":"2102.09701","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/center-smoothing-for-certifiably-robust#ran","syntology_url":"https://syntology.ai/paper/2102.09701","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.09701"}},"official":{"repos":["aounon/center-smoothing"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/effective-and-efficient-vote-attack-on-1","slug":"effective-and-efficient-vote-attack-on-1","title":"Effective and Efficient Vote Attack on Capsule Networks","date":"2021-02-19","arxiv_id":"2102.10055","repositories_listed":1,"syntology":null},{"url":"/paper/verifying-probabilistic-specifications-with","slug":"verifying-probabilistic-specifications-with","title":"Make Sure You're Unsure: A Framework for Verifying Probabilistic Specifications","date":"2021-02-18","arxiv_id":"2102.09479","repositories_listed":1,"syntology":null},{"url":"/paper/bridging-the-gap-between-adversarial","slug":"bridging-the-gap-between-adversarial","title":"Bridging the Gap Between Adversarial Robustness and Optimization Bias","date":"2021-02-17","arxiv_id":"2102.08868","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bridging-the-gap-between-adversarial#ran","syntology_url":"https://syntology.ai/paper/2102.08868","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.08868"}},"official":{"repos":["fartashf/robust_bias"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/data-profiling-for-adversarial-training-on","slug":"data-profiling-for-adversarial-training-on","title":"Data Quality Matters For Adversarial Training: An Empirical Study","date":"2021-02-15","arxiv_id":"2102.07437","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-adversarial-robustness-of-deep","slug":"exploring-adversarial-robustness-of-deep","title":"Exploring Adversarial Robustness of Deep Metric Learning","date":"2021-02-14","arxiv_id":"2102.07265","repositories_listed":1,"syntology":null},{"url":"/paper/bayesian-inference-with-certifiable","slug":"bayesian-inference-with-certifiable","title":"Bayesian Inference with Certifiable Adversarial Robustness","date":"2021-02-10","arxiv_id":"2102.05289","repositories_listed":1,"syntology":null},{"url":"/paper/optimal-transport-as-a-defense-against","slug":"optimal-transport-as-a-defense-against","title":"Optimal Transport as a Defense Against Adversarial Attacks","date":"2021-02-05","arxiv_id":"2102.03156","repositories_listed":1,"syntology":null},{"url":"/paper/learning-diverse-structured-networks-for","slug":"learning-diverse-structured-networks-for","title":"Learning Diverse-Structured Networks for Adversarial Robustness","date":"2021-02-03","arxiv_id":"2102.01886","repositories_listed":1,"syntology":null},{"url":"/paper/error-diffusion-halftoning-against","slug":"error-diffusion-halftoning-against","title":"Error Diffusion Halftoning Against Adversarial Examples","date":"2021-01-23","arxiv_id":"2101.09451","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-robustness-by-design-through","slug":"adversarial-robustness-by-design-through","title":"Adversarial Robustness by Design through Analog Computing and Synthetic Gradients","date":"2021-01-06","arxiv_id":"2101.02115","repositories_listed":1,"syntology":null},{"url":"/paper/disentangling-adversarial-robustness-in","slug":"disentangling-adversarial-robustness-in","title":"Disentangling Adversarial Robustness in Directions of the Data Manifold","date":"2021-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/generative-max-mahalanobis-classifiers-for","slug":"generative-max-mahalanobis-classifiers-for","title":"Generative Max-Mahalanobis Classifiers for Image Classification, Generation and More","date":"2021-01-01","arxiv_id":"2101.00122","repositories_listed":1,"syntology":null},{"url":"/paper/gridmix-strong-regularization-through-local","slug":"gridmix-strong-regularization-through-local","title":"GridMix: Strong regularization through local context mapping","date":"2021-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/towards-adversarial-robustness-of-bayesian","slug":"towards-adversarial-robustness-of-bayesian","title":"Towards Adversarial Robustness of Bayesian Neural Network through Hierarchical Variational Inference","date":"2021-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/better-robustness-by-more-coverage","slug":"better-robustness-by-more-coverage","title":"Better Robustness by More Coverage: Adversarial Training with Mixup Augmentation for Robust Fine-tuning","date":"2020-12-31","arxiv_id":"2012.15699","repositories_listed":1,"syntology":null},{"url":"/paper/gradient-free-adversarial-attacks-for","slug":"gradient-free-adversarial-attacks-for","title":"Gradient-Free Adversarial Attacks for Bayesian Neural Networks","date":"2020-12-23","arxiv_id":"2012.12640","repositories_listed":1,"syntology":null},{"url":"/paper/self-progressing-robust-training","slug":"self-progressing-robust-training","title":"Self-Progressing Robust Training","date":"2020-12-22","arxiv_id":"2012.11769","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-human-recognizability-phenomenon-of","slug":"on-the-human-recognizability-phenomenon-of","title":"On the human-recognizability phenomenon of adversarially trained deep image classifiers","date":"2020-12-18","arxiv_id":"2101.05219","repositories_listed":1,"syntology":null},{"url":"/paper/improving-adversarial-robustness-via-3","slug":"improving-adversarial-robustness-via-3","title":"Improving Adversarial Robustness via Probabilistically Compact Loss with Logit Constraints","date":"2020-12-14","arxiv_id":"2012.07688","repositories_listed":1,"syntology":null},{"url":"/paper/analyzing-and-improving-generative-1","slug":"analyzing-and-improving-generative-1","title":"Learning Energy-Based Models With Adversarial Training","date":"2020-12-11","arxiv_id":"2012.06568","repositories_listed":1,"syntology":null},{"url":"/paper/composite-adversarial-attacks","slug":"composite-adversarial-attacks","title":"Composite Adversarial Attacks","date":"2020-12-10","arxiv_id":"2012.05434","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/composite-adversarial-attacks#ran","syntology_url":"https://syntology.ai/paper/2012.05434","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.05434"}},"official":{"repos":["vtddggg/CAA"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/on-1-n-neural-representation-and-robustness-1","slug":"on-1-n-neural-representation-and-robustness-1","title":"On 1/n neural representation and robustness","date":"2020-12-08","arxiv_id":"2012.04729","repositories_listed":1,"syntology":null},{"url":"/paper/overcomplete-representations-against","slug":"overcomplete-representations-against","title":"Overcomplete Representations Against Adversarial Videos","date":"2020-12-08","arxiv_id":"2012.04262","repositories_listed":1,"syntology":null},{"url":"/paper/using-feature-alignment-can-improve-clean","slug":"using-feature-alignment-can-improve-clean","title":"Using Feature Alignment Can Improve Clean Average Precision and Adversarial Robustness in Object Detection","date":"2020-12-08","arxiv_id":"2012.04382","repositories_listed":1,"syntology":null},{"url":"/paper/how-robust-are-randomized-smoothing-based","slug":"how-robust-are-randomized-smoothing-based","title":"How Robust are Randomized Smoothing based Defenses to Data Poisoning?","date":"2020-12-02","arxiv_id":"2012.01274","repositories_listed":1,"syntology":null},{"url":"/paper/fast-adversarial-robustness-certification-of","slug":"fast-adversarial-robustness-certification-of","title":"Fast Adversarial Robustness Certification of Nearest Prototype Classifiers for Arbitrary Seminorms","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/on-the-trade-off-between-adversarial-and","slug":"on-the-trade-off-between-adversarial-and","title":"On the Trade-off between Adversarial and Backdoor Robustness","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/regularization-with-latent-space-virtual-1","slug":"regularization-with-latent-space-virtual-1","title":"Regularization with Latent Space Virtual Adversarial Training","date":"2020-11-26","arxiv_id":"2011.13181","repositories_listed":1,"syntology":null},{"url":"/paper/aw-nas-a-modularized-and-extensible-nas","slug":"aw-nas-a-modularized-and-extensible-nas","title":"aw_nas: A Modularized and Extensible NAS framework","date":"2020-11-25","arxiv_id":"2012.10388","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-examples-for-k-nearest-neighbor","slug":"adversarial-examples-for-k-nearest-neighbor","title":"Adversarial Examples for $k$-Nearest Neighbor Classifiers Based on Higher-Order Voronoi Diagrams","date":"2020-11-19","arxiv_id":"2011.09719","repositories_listed":1,"syntology":null},{"url":"/paper/close-category-generalization","slug":"close-category-generalization","title":"Probing Predictions on OOD Images via Nearest Categories","date":"2020-11-17","arxiv_id":"2011.08485","repositories_listed":1,"syntology":null},{"url":"/paper/siena-stochastic-multi-expert-neural-patcher","slug":"siena-stochastic-multi-expert-neural-patcher","title":"SHIELD: Defending Textual Neural Networks against Multiple Black-Box Adversarial Attacks with Stochastic Multi-Expert Patcher","date":"2020-11-17","arxiv_id":"2011.08908","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-robustness-against-image-color","slug":"adversarial-robustness-against-image-color","title":"Adversarial Image Color Transformations in Explicit Color Filter Space","date":"2020-11-12","arxiv_id":"2011.06690","repositories_listed":1,"syntology":null},{"url":"/paper/bridging-the-performance-gap-between-fgsm-and","slug":"bridging-the-performance-gap-between-fgsm-and","title":"Bridging the Performance Gap between FGSM and PGD Adversarial Training","date":"2020-11-07","arxiv_id":"2011.05157","repositories_listed":1,"syntology":null},{"url":"/paper/robust-pre-training-by-adversarial","slug":"robust-pre-training-by-adversarial","title":"Robust Pre-Training by Adversarial Contrastive Learning","date":"2020-10-26","arxiv_id":"2010.13337","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/robust-pre-training-by-adversarial#ran","syntology_url":"https://syntology.ai/paper/2010.13337","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.13337"}},"official":{"repos":["VITA-Group/Adversarial-Contrastive-Learning"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/adversarial-robustness-of-supervised-sparse","slug":"adversarial-robustness-of-supervised-sparse","title":"Adversarial Robustness of Supervised Sparse Coding","date":"2020-10-22","arxiv_id":"2010.12088","repositories_listed":1,"syntology":null},{"url":"/paper/robustbench-a-standardized-adversarial","slug":"robustbench-a-standardized-adversarial","title":"RobustBench: a standardized adversarial robustness benchmark","date":"2020-10-19","arxiv_id":"2010.09670","repositories_listed":1,"syntology":null},{"url":"/paper/a-stochastic-neural-network-for-attack","slug":"a-stochastic-neural-network-for-attack","title":"Weight-Covariance Alignment for Adversarially Robust Neural Networks","date":"2020-10-17","arxiv_id":"2010.08852","repositories_listed":1,"syntology":null},{"url":"/paper/fair-n-fair-and-robust-neural-networks-for","slug":"fair-n-fair-and-robust-neural-networks-for","title":"FaiR-N: Fair and Robust Neural Networks for Structured Data","date":"2020-10-13","arxiv_id":"2010.06113","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-power-of-abstention-and-data-driven-1","slug":"on-the-power-of-abstention-and-data-driven-1","title":"An Analysis of Robustness of Non-Lipschitz Networks","date":"2020-10-13","arxiv_id":"2010.06154","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/on-the-power-of-abstention-and-data-driven-1#ran","syntology_url":"https://syntology.ai/paper/2010.06154","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.06154"}},"official":{"repos":["dravyanshsharma/adversarial-contrastive"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/shape-texture-debiased-neural-network-1","slug":"shape-texture-debiased-neural-network-1","title":"Shape-Texture Debiased Neural Network Training","date":"2020-10-12","arxiv_id":"2010.05981","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/shape-texture-debiased-neural-network-1#ran","syntology_url":"https://syntology.ai/paper/2010.05981","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.05981"}},"official":{"repos":["LiYingwei/ShapeTextureDebiasedTraining"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/batch-normalization-increases-adversarial-1","slug":"batch-normalization-increases-adversarial-1","title":"Batch Normalization Increases Adversarial Vulnerability and Decreases Adversarial Transferability: A Non-Robust Feature Perspective","date":"2020-10-07","arxiv_id":"2010.03316","repositories_listed":1,"syntology":null},{"url":"/paper/does-network-width-really-help-adversarial","slug":"does-network-width-really-help-adversarial","title":"Do Wider Neural Networks Really Help Adversarial Robustness?","date":"2020-10-03","arxiv_id":"2010.01279","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-robustness-of-stabilized","slug":"adversarial-robustness-of-stabilized","title":"Adversarial Robustness of Stabilized NeuralODEs Might be from Obfuscated Gradients","date":"2020-09-28","arxiv_id":"2009.13145","repositories_listed":1,"syntology":null},{"url":"/paper/improving-ensemble-robustness-by","slug":"improving-ensemble-robustness-by","title":"Improving Ensemble Robustness by Collaboratively Promoting and Demoting Adversarial Robustness","date":"2020-09-21","arxiv_id":"2009.09612","repositories_listed":1,"syntology":null},{"url":"/paper/large-norms-of-cnn-layers-do-not-hurt","slug":"large-norms-of-cnn-layers-do-not-hurt","title":"Large Norms of CNN Layers Do Not Hurt Adversarial Robustness","date":"2020-09-17","arxiv_id":"2009.08435","repositories_listed":1,"syntology":null},{"url":"/paper/puzzle-mix-exploiting-saliency-and-local-1","slug":"puzzle-mix-exploiting-saliency-and-local-1","title":"Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup","date":"2020-09-15","arxiv_id":"2009.06962","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/puzzle-mix-exploiting-saliency-and-local-1#ran","syntology_url":"https://syntology.ai/paper/2009.06962","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.06962"}},"official":{"repos":["snu-mllab/PuzzleMix"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/end-to-end-kernel-learning-via-generative","slug":"end-to-end-kernel-learning-via-generative","title":"End-to-end Kernel Learning via Generative Random Fourier Features","date":"2020-09-10","arxiv_id":"2009.04614","repositories_listed":1,"syntology":null},{"url":"/paper/towards-adversarial-robustness-with-01-loss","slug":"towards-adversarial-robustness-with-01-loss","title":"Towards adversarial robustness with 01 loss neural networks","date":"2020-08-20","arxiv_id":"2008.09148","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-attack-and-defense-strategies-for","slug":"adversarial-attack-and-defense-strategies-for","title":"Adversarial Attack and Defense Strategies for Deep Speaker Recognition Systems","date":"2020-08-18","arxiv_id":"2008.07685","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-concurrent-training-optimizing","slug":"adversarial-concurrent-training-optimizing","title":"Adversarial Concurrent Training: Optimizing Robustness and Accuracy Trade-off of Deep Neural Networks","date":"2020-08-16","arxiv_id":"2008.07015","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adversarial-concurrent-training-optimizing#ran","syntology_url":"https://syntology.ai/paper/2008.07015","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.07015"}},"official":{"repos":["NeurAI-Lab/ACT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/trend-transferability-based-robust-ensemble","slug":"trend-transferability-based-robust-ensemble","title":"TREND: Transferability based Robust ENsemble Design","date":"2020-08-04","arxiv_id":"2008.01524","repositories_listed":1,"syntology":null},{"url":"/paper/neural-networks-with-recurrent-generative","slug":"neural-networks-with-recurrent-generative","title":"Neural Networks with Recurrent Generative Feedback","date":"2020-07-17","arxiv_id":"2007.09200","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/neural-networks-with-recurrent-generative#ran","syntology_url":"https://syntology.ai/paper/2007.09200","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.09200"}},"official":{"repos":["yjhuangcd/CNNF"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/an-empirical-study-on-the-robustness-of-nas","slug":"an-empirical-study-on-the-robustness-of-nas","title":"On Adversarial Robustness: A Neural Architecture Search perspective","date":"2020-07-16","arxiv_id":"2007.08428","repositories_listed":1,"syntology":null},{"url":"/paper/multitask-learning-strengthens-adversarial","slug":"multitask-learning-strengthens-adversarial","title":"Multitask Learning Strengthens Adversarial Robustness","date":"2020-07-14","arxiv_id":"2007.07236","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-robustness-via-robust-low-rank","slug":"adversarial-robustness-via-robust-low-rank","title":"Adversarial robustness via robust low rank representations","date":"2020-07-13","arxiv_id":"2007.06555","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adversarial-robustness-via-robust-low-rank#ran","syntology_url":"https://syntology.ai/paper/2007.06555","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.06555"}},"official":null}},{"url":"/paper/understanding-object-detection-through-an","slug":"understanding-object-detection-through-an","title":"Understanding Object Detection Through An Adversarial Lens","date":"2020-07-11","arxiv_id":"2007.05828","repositories_listed":1,"syntology":null},{"url":"/paper/improving-adversarial-robustness-by-enforcing","slug":"improving-adversarial-robustness-by-enforcing","title":"Improving Adversarial Robustness by Enforcing Local and Global Compactness","date":"2020-07-10","arxiv_id":"2007.05123","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/improving-adversarial-robustness-by-enforcing#ran","syntology_url":"https://syntology.ai/paper/2007.05123","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.05123"}},"official":{"repos":["tuananhbui89/Adversarial-Divergence-Reduction"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/proper-network-interpretability-helps","slug":"proper-network-interpretability-helps","title":"Proper Network Interpretability Helps Adversarial Robustness in Classification","date":"2020-06-26","arxiv_id":"2006.14748","repositories_listed":1,"syntology":{"n":17,"n_ran":6,"n_constructed":1,"n_ran_checked":3,"n_instrument":3,"n_unverified":11,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"6 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/proper-network-interpretability-helps#ran","syntology_url":"https://syntology.ai/paper/2006.14748","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.14748"}},"official":{"repos":["AkhilanB/Proper-Interpretability"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":10,"ran_from_kinds":["official"]}}},{"url":"/paper/smooth-adversarial-training","slug":"smooth-adversarial-training","title":"Smooth Adversarial Training","date":"2020-06-25","arxiv_id":"2006.14536","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/smooth-adversarial-training#ran","syntology_url":"https://syntology.ai/paper/2006.14536","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.14536"}},"official":{"repos":["cihangxie/SmoothAdversarialTraining"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/imbalanced-gradients-a-new-cause-of","slug":"imbalanced-gradients-a-new-cause-of","title":"Imbalanced Gradients: A Subtle Cause of Overestimated Adversarial Robustness","date":"2020-06-24","arxiv_id":"2006.13726","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":4,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/imbalanced-gradients-a-new-cause-of#ran","syntology_url":"https://syntology.ai/paper/2006.13726","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.13726"}},"official":{"repos":["hanxunh/mdattack"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/using-wavelets-and-spectral-methods-to-study","slug":"using-wavelets-and-spectral-methods-to-study","title":"Using Wavelets and Spectral Methods to Study Patterns in Image-Classification Datasets","date":"2020-06-17","arxiv_id":"2006.09879","repositories_listed":1,"syntology":null},{"url":"/paper/debona-decoupled-boundary-network-analysis","slug":"debona-decoupled-boundary-network-analysis","title":"Debona: Decoupled Boundary Network Analysis for Tighter Bounds and Faster Adversarial Robustness Proofs","date":"2020-06-16","arxiv_id":"2006.09040","repositories_listed":1,"syntology":null},{"url":"/paper/deterministic-gaussian-averaged-neural","slug":"deterministic-gaussian-averaged-neural","title":"Deterministic Gaussian Averaged Neural Networks","date":"2020-06-10","arxiv_id":"2006.06061","repositories_listed":1,"syntology":null}],"record_sha256":"12cf4eb7e60c753c58ae0a90026131c865b83b1c4a2973e57d64690e3e21da93","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}