{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T19:49:28Z","timestamp":1770493768253,"version":"3.49.0"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,8,31]],"date-time":"2023-08-31T00:00:00Z","timestamp":1693440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,8,31]],"date-time":"2023-08-31T00:00:00Z","timestamp":1693440000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Australian Government Research Training Program (AGRTP) Scholarship"},{"DOI":"10.13039\/501100001778","name":"Deakin University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001778","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Data Min Knowl Disc"],"published-print":{"date-parts":[[2024,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Artificial neural networks (<jats:inline-formula><jats:alternatives><jats:tex-math>$${{{\\texttt {ANN}}}}$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:mi>ANN<\/mml:mi>\n                <\/mml:math><\/jats:alternatives><\/jats:inline-formula>) are widely used machine learning models. Their widespread use has attracted a lot of interest in their robustness. Many studies show that\u00a0\u2019s performance can be highly vulnerable to input manipulation such as adversarial attacks and covariate drift. Therefore, various techniques that focus on improving <jats:inline-formula><jats:alternatives><jats:tex-math>$${{{\\texttt {ANN}}}}$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:mi>ANN<\/mml:mi>\n                <\/mml:math><\/jats:alternatives><\/jats:inline-formula>\u2019s robustness have been proposed in the last few years. However, most of these works have mostly focused on image data. In this paper, we investigate the role of discretization in improving <jats:inline-formula><jats:alternatives><jats:tex-math>$${{{\\texttt {ANN}}}}$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:mi>ANN<\/mml:mi>\n                <\/mml:math><\/jats:alternatives><\/jats:inline-formula>\u2019s robustness on tabular datasets. Two custom <jats:inline-formula><jats:alternatives><jats:tex-math>$${{{\\texttt {ANN}}}}$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:mi>ANN<\/mml:mi>\n                <\/mml:math><\/jats:alternatives><\/jats:inline-formula> layers\u2013\u00a0 and\u00a0 (collectively called\u00a0) are proposed. The two layers integrate discretization during the\u00a0<jats:italic>training phase<\/jats:italic> to improve <jats:inline-formula><jats:alternatives><jats:tex-math>$${{{\\texttt {ANN}}}}$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:mi>ANN<\/mml:mi>\n                <\/mml:math><\/jats:alternatives><\/jats:inline-formula>\u2019s ability to defend against adversarial attacks. Additionally,\u00a0 integrates dynamic discretization during\u00a0<jats:italic>testing phase<\/jats:italic> as well, to provide a unified strategy to handle adversarial attacks and covariate drift. The experimental results on 24 publicly available datasets show that our proposed\u00a0 add much-needed robustness to <jats:inline-formula><jats:alternatives><jats:tex-math>$${{{\\texttt {ANN}}}}$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:mi>ANN<\/mml:mi>\n                <\/mml:math><\/jats:alternatives><\/jats:inline-formula> for tabular datasets.<\/jats:p>","DOI":"10.1007\/s10618-023-00965-1","type":"journal-article","created":{"date-parts":[[2023,8,31]],"date-time":"2023-08-31T11:02:07Z","timestamp":1693479727000},"page":"173-205","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Improving neural network\u2019s robustness on tabular data with D-layers"],"prefix":"10.1007","volume":"38","author":[{"given":"Haiyang","family":"Xia","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nayyar","family":"Zaidi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yishuo","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,31]]},"reference":[{"key":"965_CR1","doi-asserted-by":"publisher","first-page":"14410","DOI":"10.1109\/ACCESS.2018.2807385","volume":"6","author":"N Akhtar","year":"2018","unstructured":"Akhtar N, Mian A (2018) Threat of adversarial attacks on deep learning in computer vision: a survey. IEEE Access 6:14410\u201314430","journal-title":"IEEE Access"},{"key":"965_CR2","unstructured":"Ballet V, Renard X, Aigrain J, Laugel T, Frossard P, Detyniecki M (2019) Imperceptible adversarial attacks on tabular data. arXiv preprint arXiv:1911.03274"},{"key":"965_CR3","unstructured":"Bengio Y, L\u00e9onard N, Courville A (2013) Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432"},{"issue":"9","key":"965_CR4","first-page":"2137","volume":"10","author":"S Bickel","year":"2009","unstructured":"Bickel S, Br\u00fcckner M, Scheffer T (2009) Discriminative learning under covariate shift. J Mach Learn Res 10(9):2137\u20132155","journal-title":"J Mach Learn Res"},{"key":"965_CR5","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1007\/978-3-642-03915-7_22","volume-title":"Advances in intelligent data analysis VIII","author":"A Bifet","year":"2009","unstructured":"Bifet A, Gavald\u00e0 R (2009) Adaptive learning from evolving data streams. Advances in intelligent data analysis VIII. Springer, Berlin, pp 249\u2013260"},{"key":"965_CR6","unstructured":"Buckman J, Roy A, Raffel C, Goodfellow I (2018) Thermometer encoding: One hot way to resist adversarial examples. In: International Conference on Learning Representations"},{"key":"965_CR7","unstructured":"Cartella F, Anuncia\u00e7\u00e3o O, Funabiki Y, Yamaguchi D, Akishita T, Elshocht O (2021) Adversarial attacks for tabular data: application to fraud detection and imbalanced data. In: CEUR Workshop Proceedings, vol 2808"},{"key":"965_CR8","doi-asserted-by":"crossref","unstructured":"Chen M, Zhao S, Liu H, Cai D (2020) Adversarial-learned loss for domain adaptation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol 34, pp 3521\u20133528","DOI":"10.1609\/aaai.v34i04.5757"},{"issue":"4","key":"965_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2523813","volume":"46","author":"J Gama","year":"2014","unstructured":"Gama J, \u017dliobait\u0117 I, Bifet A, Pechenizkiy M, Bouchachia A (2014) A survey on concept drift adaptation. ACM Comput Surv 46(4):1\u201337","journal-title":"ACM Comput Surv"},{"key":"965_CR10","unstructured":"Goodfellow IJ, Shlens J, Szegedy C (2014) Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572"},{"issue":"4","key":"965_CR11","first-page":"5","volume":"3","author":"A Gretton","year":"2009","unstructured":"Gretton A, Smola A, Huang J, Schmittfull M, Borgwardt K, Sch\u00f6lkopf B (2009) Covariate shift by kernel mean matching. Dataset Shift Mach Learn 3(4):5","journal-title":"Dataset Shift Mach Learn"},{"key":"965_CR12","doi-asserted-by":"publisher","first-page":"100270","DOI":"10.1016\/j.cosrev.2020.100270","volume":"37","author":"X Huang","year":"2020","unstructured":"Huang X, Kroening D, Ruan W, Sharp J, Sun Y, Thamo E, Wu M, Yi X (2020) A survey of safety and trustworthiness of deep neural networks: verification, testing, adversarial attack and defence, and interpretability. Comput Sci Rev 37:100270","journal-title":"Comput Sci Rev"},{"key":"965_CR13","unstructured":"Ioffe S, Szegedy C (2015) Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning. PMLR"},{"key":"965_CR14","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/4907754","author":"Z Kong","year":"2021","unstructured":"Kong Z, Xue J, Wang Y, Huang L, Niu Z, Li F (2021) A survey on adversarial attack in the age of artificial intelligence. Wirel Commun Mobile Comput. https:\/\/doi.org\/10.1155\/2021\/4907754","journal-title":"Wirel Commun Mobile Comput"},{"key":"965_CR15","doi-asserted-by":"crossref","unstructured":"Kumov\u00e1 V, Pil\u00e1t M (2021) Beating white-box defenses with black-box attacks. In: 2021 International Joint Conference on Neural Networks (IJCNN). IEEE, pp 1\u20138","DOI":"10.1109\/IJCNN52387.2021.9533772"},{"key":"965_CR16","unstructured":"Kurakin A, Goodfellow IJ, Bengio S (2017) Adversarial machine learning at scale. In: 5th International Conference on Learning Representations, ICLR 2017 - Conference Track Proceedings"},{"key":"965_CR17","unstructured":"Kurakin A, Goodfellow I, Bengio S (2016) Adversarial machine learning at scale. arXiv preprint arXiv:1611.01236"},{"key":"965_CR18","unstructured":"Li F, Lam H, Prusty S (2020) Robust importance weighting for covariate shift. In: International Conference on Artificial Intelligence and Statistics. PMLR, pp 352\u2013362"},{"key":"965_CR19","unstructured":"Madry A, Makelov A, Schmidt L, Tsipras D, Vladu A (2017) Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083"},{"key":"965_CR20","unstructured":"Magliacane S, van Ommen T, Claassen T, Bongers S, Versteeg P, Mooij JM (2017) Domain adaptation by using causal inference to predict invariant conditional distributions. arXiv preprint arXiv:1707.06422"},{"key":"965_CR21","doi-asserted-by":"crossref","unstructured":"Moosavi-Dezfooli S-M, Fawzi A, Frossard P (2016) Deepfool: a simple and accurate method to fool deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 2574\u20132582","DOI":"10.1109\/CVPR.2016.282"},{"key":"965_CR22","unstructured":"Nado Z, Padhy S, Sculley D, D\u2019Amour A, Lakshminarayanan B, Snoek J (2020) Evaluating prediction-time batch normalization for robustness under covariate shift. arXiv preprint arXiv:2006.10963"},{"key":"965_CR23","unstructured":"Nair NG, Satpathy P, Christopher J, et\u00a0al (2019) Covariate shift: A review and analysis on classifiers. In: 2019 Global Conference for Advancement in Technology (GCAT). IEEE, pp 1\u20136"},{"key":"965_CR24","first-page":"105","volume-title":"Artificial intelligence and statistics","author":"N Oza","year":"2001","unstructured":"Oza N, Russell S (2001) Online bagging and boosting. Artificial intelligence and statistics. Morgan Kaufmann, San Francisco, pp 105\u2013112"},{"key":"965_CR25","unstructured":"Pathak R, Ma C, Wainwright M (2022) A new similarity measure for covariate shift with applications to nonparametric regression. In: International Conference on Machine Learning. PMLR, pp 17517\u201317530"},{"key":"965_CR26","doi-asserted-by":"crossref","unstructured":"Pfahringer B, Holmes G, Kirkby R (2007) New options for Hoeffding trees. In: AI 2007: Advances in Artificial Intelligence vol 4830. Springer, pp 90\u201399","DOI":"10.1007\/978-3-540-76928-6_11"},{"key":"965_CR27","unstructured":"Shafahi A, Najibi M, Ghiasi A, Xu Z, Dickerson J, Studer C, Davis LS, Taylor G, Goldstein T (2019) Adversarial training for free! In: Advances in Neural Information Processing Systems, vol 32"},{"issue":"5","key":"965_CR28","first-page":"985","volume":"8","author":"M Sugiyama","year":"2007","unstructured":"Sugiyama M, Krauledat M, M\u00fcller K-R (2007) Covariate shift adaptation by importance weighted cross validation. J Mach Learn Res 8(5):985\u20131005","journal-title":"J Mach Learn Res"},{"key":"965_CR29","unstructured":"Van Den Oord A, Vinyals O et al (2017) Neural discrete representation learning. Advances in neural information processing systems 30"},{"key":"965_CR30","doi-asserted-by":"crossref","unstructured":"Wang B, Qiu M, Wang X, Li Y, Gong Y, Zeng X, Huang J, Zheng B, Cai D, Zhou J (2019) A minimax game for instance based selective transfer learning. In: Proceedings of the 25th ACM SIGKDD","DOI":"10.1145\/3292500.3330841"},{"key":"965_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3400066","volume":"11","author":"G Wilson","year":"2020","unstructured":"Wilson G, Cook DJ (2020) A survey of unsupervised deep domain adaptation. ACM Trans Intell Syst Technol 11:1\u201346","journal-title":"ACM Trans Intell Syst Technol"},{"key":"965_CR32","unstructured":"Yu Z, Wang P, Xu J, Xie L, Jin Z, Huang J, He X, Cai D, Hua X-S (2020) Stable learning via causality-based feature rectification. CoRR"},{"key":"965_CR33","unstructured":"Zhang T, Yamane I, Lu N, Sugiyama M (2020) A one-step approach to covariate shift adaptation. In: Asian Conference on Machine Learning. PMLR, pp 65\u201380"},{"key":"965_CR34","doi-asserted-by":"crossref","unstructured":"Zhou J, Zaidi N, Zhang Y, Li G (2022) Discretization inspired defence algorithm against adversarial attacks on tabular data. In: Pacific-Asia Conference on Knowledge Discovery and Data Mining. Springer, pp 367\u2013379","DOI":"10.1007\/978-3-031-05936-0_29"},{"key":"965_CR35","doi-asserted-by":"crossref","unstructured":"Zhou J, Zaidi N, Zhang Y, Montague P, Kim J, Li G (2023) Leveraging generative models for combating adversarial attacks on tabular datasets. In: Pacific-Asia Conference on Knowledge Discovery and Data Mining. Springer, pp 147\u2013158","DOI":"10.1007\/978-3-031-33374-3_12"}],"container-title":["Data Mining and Knowledge Discovery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10618-023-00965-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10618-023-00965-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10618-023-00965-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T17:50:55Z","timestamp":1705513855000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10618-023-00965-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,31]]},"references-count":35,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,1]]}},"alternative-id":["965"],"URL":"https:\/\/doi.org\/10.1007\/s10618-023-00965-1","relation":{},"ISSN":["1384-5810","1573-756X"],"issn-type":[{"value":"1384-5810","type":"print"},{"value":"1573-756X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,31]]},"assertion":[{"value":"16 January 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 July 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 August 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Authors do not have any funding information to report. Authors do have any actual, perceived or potential conflict of interests (financial or non-financial) to disclose as well.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}