{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T20:15:22Z","timestamp":1782764122826,"version":"3.54.5"},"reference-count":214,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"A*STAR Center for Frontier AI Research"},{"DOI":"10.13039\/501100001475","name":"Nanyang Technological University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001475","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Comput. Intell. Mag."],"published-print":{"date-parts":[[2023,5]]},"DOI":"10.1109\/mci.2023.3245733","type":"journal-article","created":{"date-parts":[[2023,4,13]],"date-time":"2023-04-13T17:34:46Z","timestamp":1681407286000},"page":"60-77","source":"Crossref","is-referenced-by-count":51,"title":["Survey on AI Sustainability: Emerging Trends on Learning Algorithms and Research Challenges [Review Article]"],"prefix":"10.1109","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1719-0328","authenticated-orcid":false,"given":"Zhenghua","family":"Chen","sequence":"first","affiliation":[{"name":"Agency for Science, Technology and Research (A*STAR), Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0977-3600","authenticated-orcid":false,"given":"Min","family":"Wu","sequence":"additional","affiliation":[{"name":"Agency for Science, Technology and Research (A*STAR), Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1041-3891","authenticated-orcid":false,"given":"Alvin","family":"Chan","sequence":"additional","affiliation":[{"name":"Agency for Science, Technology and Research (A*STAR) and Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0762-6562","authenticated-orcid":false,"given":"Xiaoli","family":"Li","sequence":"additional","affiliation":[{"name":"Agency for Science, Technology and Research (A*STAR) and Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4480-169X","authenticated-orcid":false,"given":"Yew-Soon","family":"Ong","sequence":"additional","affiliation":[{"name":"Agency for Science, Technology and Research (A*STAR) and Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2982166"},{"key":"ref2","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10639-019-10063-9"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1142\/11784"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2018.05.050"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2007.06.002"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCTCT.2018.8551185"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2016.07.004"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref10","article-title":"Sustainable AI: An inventory of the state of knowledge of ethical, social, and legal challenges related to artificial intelligence","author":"Larsson","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s43681-021-00043-6"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i09.7123"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-020-09517-8"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1080\/23311886.2019.1653531"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/su132112064"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-14108-y"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3381831"},{"key":"ref18","article-title":"Training a single AI model can emit as much carbon as five cars in their lifetimes","volume":"75","author":"Hao","year":"2019","journal-title":"MIT Technol. Rev."},{"key":"ref19","article-title":"Carbon emissions and large neural network training","author":"Patterson","year":"2021"},{"key":"ref20","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"25","author":"Krizhevsky","year":"2012"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966166"},{"key":"ref23","first-page":"598","article-title":"Optimal brain damage","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"LeCun","year":"1990"},{"key":"ref24","first-page":"2148","article-title":"Predicting parameters in deep learning","volume-title":"Proc. 26th Int. Conf. Neural Inf. Process. Syst.","volume":"2","author":"Denil","year":"2013"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09816-7"},{"key":"ref26","article-title":"Learning both weights and connections for efficient neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Han","year":"2015"},{"key":"ref27","article-title":"Pruning filters for efficient convnets","author":"Li","year":"2016"},{"key":"ref28","first-page":"177","article-title":"Comparing biases for minimal network construction with back-propagation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hanson","year":"1988"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.07.045"},{"key":"ref30","first-page":"2074","article-title":"Learning structured sparsity in deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wen","year":"2016"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref32","article-title":"Network trimming: A data-driven neuron pruning approach towards efficient deep architectures","author":"Hu","year":"2016"},{"key":"ref33","volume-title":"Second Order Derivatives for Network Pruning: Optimal Brain Surgeon","author":"Hassibi","year":"1993"},{"key":"ref34","article-title":"Snip: Single-shot network pruning based on connection sensitivity","author":"Lee","year":"2018"},{"key":"ref35","article-title":"Jack and masters of all trades: One-pass learning of a set of model sets from foundation models","author":"Choong","year":"2022"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00083"},{"key":"ref37","article-title":"Comparing rewinding and fine-tuning in neural network pruning","author":"Renda","year":"2020"},{"key":"ref38","article-title":"Picking winning tickets before training by preserving gradient flow","author":"Wang","year":"2020"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-018-04316-3"},{"key":"ref40","first-page":"1737","article-title":"Deep learning with limited numerical precision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gupta","year":"2015"},{"key":"ref41","article-title":"Improving the speed of neural networks on CPUs","volume-title":"Proc. Deep Learn. Unsupervised Feature Learn. Workshop","author":"Vanhoucke","year":"2011"},{"key":"ref42","article-title":"Binarized neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Hubara","year":"2016"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref45","article-title":"Incremental network quantization: Towards lossless CNNs with low-precision weights","author":"Zhou","year":"2017"},{"key":"ref46","article-title":"DOREFA-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients","author":"Zhou","year":"2016"},{"key":"ref47","article-title":"Compressing deep convolutional networks using vector quantization","author":"Gong","year":"2014"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.521"},{"key":"ref49","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","author":"Han","year":"2015"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3055564"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref52","article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. NIPS Deep Learn. Representation Learn. Workshop","volume":"1050","author":"Hinton","year":"2014"},{"key":"ref53","article-title":"FITNets: Hints for thin deep nets","author":"Romero","year":"2014"},{"key":"ref54","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Komodakis","year":"2017"},{"key":"ref55","article-title":"Graph-based knowledge distillation by multi-head attention network","author":"Lee","year":"2019"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref57","article-title":"Contrastive representation distillation","author":"Tian","year":"2019"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_21"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.754"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-614"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17680"},{"key":"ref62","first-page":"1607","article-title":"Born again neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Furlanello","year":"2018"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00454"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2021.3057030"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01065"},{"key":"ref66","article-title":"Full-cycle energy consumption benchmark for low-carbon computer vision","author":"Li","year":"2021"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3472291"},{"key":"ref69","article-title":"Active learning literature survey","author":"Settles","year":"2009","journal-title":"Technical Report"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K19-1044"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2014.04.034"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00236"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00945"},{"key":"ref74","article-title":"Deep active learning over the long tail","author":"Geifman","year":"2017"},{"key":"ref75","article-title":"Few-shot learning: A survey","author":"Wang","year":"2019"},{"key":"ref76","article-title":"Meta-learning: A survey","author":"Vanschoren","year":"2018"},{"key":"ref77","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn","year":"2017"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01199"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414936"},{"key":"ref80","article-title":"Siamese neural networks for one-shot image recognition","volume-title":"Proc. Int. Conf. Mach. Learn. Deep Learn. Workshop","author":"Koch","year":"2015"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24261-3_7"},{"key":"ref82","first-page":"3630","article-title":"Matching networks for one shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vinyals","year":"2016"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295163"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-3357-7_7"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00529"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00792"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref89","article-title":"Deep domain confusion: Maximizing for domain invariance","author":"Tzeng","year":"2014"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5745"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-58347-1_8"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30671-7_6"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.316"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.5555\/2946645.2946704"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/439"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/440"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00494"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref100","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref104","article-title":"Unsupervised representation learning by predicting image rotations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Komodakis","year":"2018"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_35"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00577"},{"key":"ref108","article-title":"Shuffle to learn: Self-supervised learning from permutations via differentiable ranking","author":"Carr","year":"2020"},{"key":"ref109","article-title":"Efficient estimation of word representations in vector space","author":"Mikolov","year":"2013"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2019.2928344"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287563"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1145\/3306618.3314244"},{"key":"ref113","first-page":"1670","article-title":"Recommendations as treatments: Debiasing learning and evaluation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schnabel","year":"2016"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1145\/3457607"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1145\/3564284"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1145\/3616865"},{"key":"ref117","first-page":"325","article-title":"Learning fair representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zemel","year":"2013"},{"key":"ref118","first-page":"3315","article-title":"Equality of opportunity in supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hardt","year":"2016"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1145\/2090236.2090255"},{"key":"ref120","article-title":"AI fairness 360: An extensible toolkit for detecting, understanding, and mitigating unwanted algorithmic bias","author":"Bellamy","year":"2018"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-011-0463-8"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783311"},{"key":"ref123","first-page":"702","article-title":"Identifying and correcting label bias in machine learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Jiang","year":"2020"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/201"},{"key":"ref125","first-page":"962","article-title":"Fairness constraints: Mechanisms for fair classification","author":"Zafar","year":"2017","journal-title":"Proc. Artif. Intell. Statist."},{"key":"ref126","first-page":"2737","article-title":"Nonconvex optimization for regression with fairness constraints","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Komiyama","year":"2018"},{"key":"ref127","article-title":"Enhancing the accuracy and fairness of human decision making","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Valera","year":"2018"},{"key":"ref128","article-title":"Translation tutorial: 21 fairness definitions and their politics","volume":"1170","author":"Narayanan","year":"2018","journal-title":"Proc. Conf. Fairness Accountability Transp."},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467326"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16986"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1145\/3298981"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2017.2659498"},{"key":"ref133","first-page":"4427","article-title":"Federated multi-task learning","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Smith","year":"2017"},{"key":"ref134","article-title":"Federated learning: Strategies for improving communication efficiency","author":"Kone\u010dn\u00fd","year":"2016"},{"key":"ref135","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Int. Conf. Artif. Intell., Statist.","author":"McMahan","year":"2017"},{"key":"ref136","article-title":"On the convergence of FedAvg on non-IID data","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2019"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737464"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2019.00099"},{"key":"ref139","article-title":"Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption","author":"Hardy","year":"2017"},{"key":"ref140","article-title":"Parallel distributed logistic regression for vertical federated learning without third-party coordinator","author":"Yang","year":"2019"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2021.3082561"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.14778\/3407790.3407811"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2021.3124599"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2020.2988525"},{"key":"ref145","article-title":"Federated adversarial domain adaptation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Peng","year":"2020"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00107"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1561\/9781680837896"},{"key":"ref148","volume-title":"Interpretable Machine Learning","author":"Molnar","year":"2020"},{"key":"ref149","article-title":"Rule-based classification","volume-title":"Proc. Data Classification: Algorithms Appl.","author":"Li","year":"2013"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.2307\/2699986"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-3020"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11491"},{"key":"ref153","article-title":"Counterfactual explanations for machine learning: A review","volume":"32","author":"Verma","year":"2020"},{"key":"ref154","article-title":"Examples are not enough, learn to criticize! Criticism for interpretability","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Kim","year":"2016"},{"key":"ref155","first-page":"1885","article-title":"Understanding black-box predictions via influence functions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Koh","year":"2017"},{"key":"ref156","article-title":"Intriguing properties of neural networks","author":"Szegedy","year":"2013"},{"key":"ref157","article-title":"Technical report on the cleverhans v2.1.0 adversarial examples library","author":"Papernot","year":"2018"},{"key":"ref158","first-page":"2206","article-title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Croce","year":"2020"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2018.00009"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1145\/3460120.3484742"},{"key":"ref161","article-title":"Adversarial attacks and defenses for speech recognition systems","author":"\u017belasko","year":"2021"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1215"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-019-1211-x"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.263"},{"key":"ref165","article-title":"Towards deep learning models resistant to adversarial attacks","author":"Madry","year":"2017"},{"key":"ref166","article-title":"Theoretically principled trade-off between robustness and accuracy","author":"Zhang","year":"2019"},{"key":"ref167","article-title":"Adversarial training for free!","author":"Shafahi","year":"2019"},{"key":"ref168","first-page":"11278","article-title":"Attacks which do not kill training make adversarial learning stronger","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang","year":"2020"},{"key":"ref169","article-title":"Adversarial logit pairing","author":"Kannan","year":"2018"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00059"},{"key":"ref171","article-title":"Robust overfitting may be mitigated by properly learned smoothening","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2020"},{"key":"ref172","first-page":"16048","article-title":"Understanding and improving fast adversarial training","author":"Andriushchenko","year":"2020"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1991.155328"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11504"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_32"},{"key":"ref176","first-page":"1823","article-title":"On the connection between adversarial robustness and saliency map interpretability","author":"Etmann","year":"2019"},{"key":"ref177","article-title":"Jacobian adversarially regularized networks for robustness","author":"Chan","year":"2019"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00041"},{"key":"ref179","first-page":"2266","article-title":"Formal guarantees on the robustness of a classifier against adversarial manipulation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hein","year":"2017"},{"key":"ref180","first-page":"10877","article-title":"Semidefinite relaxations for certifying robustness to adversarial examples","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Raghunathan","year":"2018"},{"key":"ref181","first-page":"1310","article-title":"Certified adversarial robustness via randomized smoothing","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cohen","year":"2019"},{"key":"ref182","article-title":"Adversarial training and provable defenses: Bridging the gap","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Balunovic","year":"2019"},{"key":"ref183","first-page":"1","article-title":"Random smoothing might be unable to certify $\\ell _{\\infty }$\u2113\u221e robustness for high-dimensional images","volume":"21","author":"Blum","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref184","first-page":"1","article-title":"Exploiting machine learning to subvert your spam filter","volume-title":"Proc. 1st Usenix Workshop Large-Scale Exploits Emergent Threats","author":"Nelson","year":"2008"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2014.08.081"},{"key":"ref186","first-page":"3517","article-title":"Certified defenses for data poisoning attacks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Steinhardt","year":"2017"},{"key":"ref187","article-title":"BADNets: Identifying vulnerabilities in the machine learning model supply chain","author":"Gu","year":"2017"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2018.23291"},{"key":"ref189","first-page":"1615","article-title":"Turning your weakness into a strength: Watermarking deep neural networks by backdooring","volume-title":"Proc. 27th USENIX Secur. Symp.","author":"Adi","year":"2018"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.373"},{"key":"ref191","first-page":"8011","article-title":"Spectral signatures in backdoor attacks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tran","year":"2018"},{"key":"ref192","first-page":"14004","article-title":"Defending neural backdoors via generative distribution modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Qiao","year":"2019"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00031"},{"key":"ref194","article-title":"Detecting backdoor attacks on deep neural networks by activation clustering","author":"Chen","year":"2018"},{"key":"ref195","article-title":"Poison as a cure: Detecting & neutralizing variable-sized backdoor attacks in deep neural networks","author":"Chan","year":"2019"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00470-5_13"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/657"},{"key":"ref198","first-page":"8230","article-title":"Certified robustness to label-flipping attacks via randomized smoothing","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rosenfeld","year":"2020"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/sp46215.2023.10179451"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCN.2017.8038465"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01501"},{"key":"ref202","article-title":"Autoaugment: Learning augmentation policies from data","author":"Cubuk","year":"2018"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00823"},{"key":"ref204","article-title":"On the effectiveness of adversarial training against common corruptions","author":"Kireev","year":"2021"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1923-7"},{"key":"ref206","first-page":"1","article-title":"Efficient large-scale language model training on GPU clusters using Megatron-LM","volume-title":"Proc. Int. Conf. High Perform. Comput., Netw., Storage Anal.","author":"Narayanan","year":"2021"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3216981"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.2200\/s00960ed2v01y201910aim043"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.03.010"},{"key":"ref210","first-page":"1653","article-title":"A neural-symbolic cognitive agent for online learning and reasoning","volume-title":"Proc. 32nd Int. Joint Conf. Artif. Intell.","author":"Penning","year":"2011"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref212","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown","year":"2020"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.3030418"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1109\/Trustcom.2015.485"}],"container-title":["IEEE Computational Intelligence Magazine"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10207\/10102373\/10102375.pdf?arnumber=10102375","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T02:06:25Z","timestamp":1709258785000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10102375\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5]]},"references-count":214,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/mci.2023.3245733","relation":{},"ISSN":["1556-603X","1556-6048"],"issn-type":[{"value":"1556-603X","type":"print"},{"value":"1556-6048","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5]]}}}