{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T22:28:08Z","timestamp":1786487288591,"version":"build-2736575974"},"reference-count":47,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","award":["101133807"],"award-info":[{"award-number":["101133807"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.neucom.2026.134666","type":"journal-article","created":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T06:47:50Z","timestamp":1785394070000},"page":"134666","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Detecting and mitigating training anomalies in deep neural networks"],"prefix":"10.1016","volume":"702","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5773-2783","authenticated-orcid":false,"given":"Vasilios","family":"Moustakidis","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1177-9139","authenticated-orcid":false,"given":"Nikolaos","family":"Passalis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1288-3667","authenticated-orcid":false,"given":"Anastasios","family":"Tefas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.134666_bib0005","doi-asserted-by":"crossref","first-page":"1956","DOI":"10.1007\/s11263-020-01316-z","article-title":"The open images dataset v4: unified image classification, object detection, and visual relationship detection at scale","volume":"128","author":"Kuznetsova","year":"2020","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.neucom.2026.134666_bib0010","series-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing and the International Joint Conference on Natural Language Processing","first-page":"188","article-title":"Justifying recommendations using distantly-labeled reviews and fine-grained aspects","author":"Ni","year":"2019"},{"key":"10.1016\/j.neucom.2026.134666_bib0015","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3514496","article-title":"Runtime adaptation of data stream processing systems: the state of the art","volume":"54","author":"Cardellini","year":"2022","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.neucom.2026.134666_bib0020","author":"Szegedy"},{"key":"10.1016\/j.neucom.2026.134666_bib0025","series-title":"Proceedings of the International Conference on Machine Learning","first-page":"274","article-title":"Obfuscated gradients give a false sense of security: circumventing defenses to adversarial examples","author":"Athalye","year":"2018"},{"key":"10.1016\/j.neucom.2026.134666_bib0030","author":"Chen"},{"key":"10.1016\/j.neucom.2026.134666_bib0035","series-title":"Clean-Label Backdoor Attacks","author":"Turner","year":"2018"},{"key":"10.1016\/j.neucom.2026.134666_bib0040","series-title":"International Conference on Machine Learning","first-page":"2304","article-title":"Mentornet: learning data-driven curriculum for very deep neural networks on corrupted labels","author":"Jiang","year":"2018"},{"key":"10.1016\/j.neucom.2026.134666_bib0045","series-title":"Proceedings of the IEEE Security and Privacy Workshops","first-page":"69","article-title":"Adversarial machine learning-industry perspectives","author":"Kumar","year":"2020"},{"key":"10.1016\/j.neucom.2026.134666_bib0050","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3439950","article-title":"Deep learning for anomaly detection: a review","volume":"54","author":"Pang","year":"2021","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.neucom.2026.134666_bib0055","series-title":"Proceedings of the 26th Annual International Conference on Machine Learning","first-page":"41","article-title":"Curriculum learning","author":"Bengio","year":"2009"},{"key":"10.1016\/j.neucom.2026.134666_bib0060","article-title":"Certified defenses for data poisoning attacks","volume":"30","author":"Steinhardt","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134666_bib0065","author":"Madry"},{"key":"10.1016\/j.neucom.2026.134666_bib0070","series-title":"Proceedings of the ACM on Asia Conference on Computer and Communications Security","first-page":"506","article-title":"Practical black-box attacks against machine learning","author":"Papernot","year":"2017"},{"key":"10.1016\/j.neucom.2026.134666_bib0075","article-title":"Poison frogs! Targeted clean-label poisoning attacks on neural networks","volume":"31","author":"Shafahi","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134666_bib0080","series-title":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","first-page":"69","article-title":"Activation anomaly analysis","author":"Sperl","year":"2020"},{"key":"10.1016\/j.neucom.2026.134666_bib0085","series-title":"European Conference on Computer Vision","first-page":"206","article-title":"Backpropagated gradient representations for anomaly detection","author":"Kwon","year":"2020"},{"key":"10.1016\/j.neucom.2026.134666_bib0090","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"Rumelhart","year":"1986","journal-title":"Nature"},{"key":"10.1016\/j.neucom.2026.134666_bib0095","first-page":"19365","article-title":"Self-adaptive training: beyond empirical risk minimization","volume":"33","author":"Huang","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134666_bib0100","first-page":"14207","article-title":"Gradaug: a new regularization method for deep neural networks","volume":"33","author":"Yang","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134666_bib0105","series-title":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","first-page":"237","article-title":"Learning with noisy labels by adaptive gradient-based outlier removal","author":"Sedova","year":"2023"},{"key":"10.1016\/j.neucom.2026.134666_bib0110","author":"Yang"},{"key":"10.1016\/j.neucom.2026.134666_bib0115","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1016\/j.neucom.2019.09.078","article-title":"Robust deep auto-encoding Gaussian process regression for unsupervised anomaly detection","volume":"376","author":"Fan","year":"2020","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134666_bib0120","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.126634","article-title":"Meta-survey on outlier and anomaly detection","volume":"555","author":"Olteanu","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134666_bib0125","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.132249","article-title":"Normality-calibrated autoencoder for unsupervised anomaly detection on data contamination","volume":"667","author":"Yu","year":"2026","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134666_bib0130","doi-asserted-by":"crossref","first-page":"372","DOI":"10.1016\/j.neucom.2021.04.033","article-title":"Autoencoder framework based on orthogonal projection constraints improves anomalies detection","volume":"450","author":"Yu","year":"2021","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134666_bib0135","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3627536","article-title":"The path to defence: a roadmap to characterising data poisoning attacks on victim models","volume":"56","author":"Chaalan","year":"2024","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.neucom.2026.134666_bib0140","author":"Tschannen"},{"key":"10.1016\/j.neucom.2026.134666_bib0145","author":"Lewandowski"},{"key":"10.1016\/j.neucom.2026.134666_bib0150","series-title":"NIPS Workshop on Deep Learning and Unsupervised Feature Learning","first-page":"4","article-title":"Reading digits in natural images with unsupervised feature learning","author":"Netzer","year":"2011"},{"key":"10.1016\/j.neucom.2026.134666_bib0155","series-title":"Learning Multiple Layers of Features From Tiny Images","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.neucom.2026.134666_bib0160","series-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"248","article-title":"Imagenet: a large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.neucom.2026.134666_bib0165","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.neucom.2026.134666_bib0170","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"4510","article-title":"MobileNetV2: inverted residuals and linear bottlenecks","author":"Sandler","year":"2018"},{"key":"10.1016\/j.neucom.2026.134666_bib0175","article-title":"Sparse Autoencoder","volume":"72","author":"Ng","year":"2011"},{"key":"10.1016\/j.neucom.2026.134666_bib0180","author":"Hendrycks"},{"key":"10.1016\/j.neucom.2026.134666_bib0185","doi-asserted-by":"crossref","first-page":"1122","DOI":"10.1016\/j.cell.2018.02.010","article-title":"Identifying medical diagnoses and treatable diseases by image-based deep learning","volume":"172","author":"Kermany","year":"2018","journal-title":"Cell"},{"key":"10.1016\/j.neucom.2026.134666_bib0190","series-title":"International Conference on Machine Learning","first-page":"1062","article-title":"Understanding and utilizing deep neural networks trained with noisy labels","author":"Chen","year":"2019"},{"key":"10.1016\/j.neucom.2026.134666_bib0195","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"3326","article-title":"O2u-Net: a simple noisy label detection approach for deep neural networks","author":"Huang","year":"2019"},{"key":"10.1016\/j.neucom.2026.134666_bib0200","series-title":"International Conference on Machine Learning","first-page":"3763","article-title":"Robust inference via generative classifiers for handling noisy labels","author":"Lee","year":"2019"},{"key":"10.1016\/j.neucom.2026.134666_bib0205","author":"Zhang"},{"key":"10.1016\/j.neucom.2026.134666_bib0210","article-title":"Generalized cross entropy loss for training deep neural networks with noisy labels","volume":"31","author":"Zhang","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134666_bib0215","doi-asserted-by":"crossref","first-page":"1526","DOI":"10.1007\/s11263-022-01611-x","article-title":"Curriculum learning: a survey","volume":"130","author":"Soviany","year":"2022","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.neucom.2026.134666_bib0220","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"24585","article-title":"The dark side of dynamic routing neural networks: towards efficiency backdoor injection","author":"Chen","year":"2023"},{"key":"10.1016\/j.neucom.2026.134666_bib0225","series-title":"Proceedings of the 35th Annual Computer Security Applications Conference","first-page":"113","article-title":"Strip: a defence against trojan attacks on deep neural networks","author":"Gao","year":"2019"},{"key":"10.1016\/j.neucom.2026.134666_bib0230","author":"Chen"},{"key":"10.1016\/j.neucom.2026.134666_bib0235","doi-asserted-by":"crossref","first-page":"11947","DOI":"10.52202\/068431-0868","article-title":"Friendly noise against adversarial noise: a powerful defense against data poisoning attack","volume":"35","author":"Liu","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226020643?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226020643?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T21:39:23Z","timestamp":1786484363000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226020643"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":47,"alternative-id":["S0925231226020643"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134666","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Detecting and mitigating training anomalies in deep neural networks","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134666","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"134666"}}