{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T23:03:42Z","timestamp":1773270222212,"version":"3.50.1"},"reference-count":38,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100010945","name":"University of California Merced","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010945","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.eswa.2026.131501","type":"journal-article","created":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T17:18:56Z","timestamp":1770311936000},"page":"131501","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Roughness-informed differential privacy"],"prefix":"10.1016","volume":"313","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9013-291X","authenticated-orcid":false,"given":"Mohammad","family":"Partohaghighi","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6838-140X","authenticated-orcid":false,"given":"Roummel","family":"Marcia","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4961-1542","authenticated-orcid":false,"given":"Bruce J.","family":"West","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7422-5988","authenticated-orcid":false,"given":"Yangquan","family":"Chen","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.131501_bib0001","series-title":"Proceedings of the 2016 acm sigsac conference on computer and communications security (ccs)","first-page":"308","article-title":"Deep learning with differential privacy","author":"Abadi","year":"2016"},{"key":"10.1016\/j.eswa.2026.131501_bib0002","series-title":"Acm sigkdd international conference on knowledge discovery & data mining (kdd)","first-page":"2867","article-title":"Census bureau adopts differential privacy","author":"Abowd","year":"2018"},{"key":"10.1016\/j.eswa.2026.131501_bib0003","series-title":"2014 Ieee 55th annual symposium on foundations of computer science (focs)","first-page":"464","article-title":"Private empirical risk minimization: Efficient algorithms and tight error bounds","author":"Bassily","year":"2014"},{"key":"10.1016\/j.eswa.2026.131501_bib0004","series-title":"Technical Report","article-title":"A note on differential privacy of federated learning","author":"Bellet","year":"2022"},{"key":"10.1016\/j.eswa.2026.131501_bib0005","series-title":"Technical Report","article-title":"Differentially private fine-tuned NF-Net to predict GI cancer type","author":"Chilukoti","year":"2025"},{"key":"10.1016\/j.eswa.2026.131501_bib0006","series-title":"Technical Report","author":"Dua","year":"2019"},{"key":"10.1016\/j.eswa.2026.131501_bib0007","series-title":"Theory of cryptography conference (tcc)","first-page":"265","article-title":"Calibrating noise to sensitivity in private data analysis","author":"Dwork","year":"2006"},{"key":"10.1016\/j.eswa.2026.131501_bib0008","series-title":"The algorithmic foundations of differential privacy","author":"Dwork","year":"2014"},{"key":"10.1016\/j.eswa.2026.131501_bib0009","series-title":"A recent survey on privacy-preserving machine learning with fully homomorphic encryption, Advances in Computers","volume":"vol. 128","author":"Gong","year":"2023"},{"key":"10.1016\/j.eswa.2026.131501_bib0010","series-title":"International conference on machine learning (icml)","first-page":"4387","article-title":"The non-iid data quagmire of decentralized machine learning","author":"Hsieh","year":"2020"},{"key":"10.1016\/j.eswa.2026.131501_bib0011","series-title":"Technical Report","article-title":"Learning multiple layers of features from tiny images, Master\u2019s thesis","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.eswa.2026.131501_bib0012","series-title":"Advances in neural information processing systems (neurips)","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"Krizhevsky","year":"2012"},{"key":"10.1016\/j.eswa.2026.131501_bib0013","series-title":"Gradient-based learning applied to document recognition","volume":"vol. 86","author":"Lecun","year":"1998"},{"key":"10.1016\/j.eswa.2026.131501_bib0014","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume":"2","author":"Li","year":"2020","journal-title":"Proceedings of Machine Learning and Systems (MLSys)"},{"key":"10.1016\/j.eswa.2026.131501_bib0015","series-title":"Technical Report","article-title":"On the Dirichlet distribution","author":"Lin","year":"2016"},{"key":"10.1016\/j.eswa.2026.131501_bib0016","series-title":"Artificial intelligence and statistics (aistats)","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"Mcmahan","year":"2017"},{"key":"10.1016\/j.eswa.2026.131501_bib0017","series-title":"Acm sigmod international conference on management of data","first-page":"19","article-title":"Privacy integrated queries: An extensible platform for privacy-preserving data analysis","author":"Mcsherry","year":"2009"},{"key":"10.1016\/j.eswa.2026.131501_bib0018","series-title":"Technical Report","article-title":"R\u00e9nyi differential privacy of the sampled Gaussian mechanism","author":"Mironov","year":"2019"},{"key":"10.1016\/j.eswa.2026.131501_bib0019","series-title":"2021 Ieee symposium on security and privacy (sp)","first-page":"866","article-title":"Adversary instantiation: Lower bounds for differentially private machine learning","author":"Nasr","year":"2021"},{"key":"10.1016\/j.eswa.2026.131501_bib0020","series-title":"Vehicle energy dataset (ved), a large-scale dataset for vehicle energy consumption research","first-page":"1","author":"Oh","year":"2020"},{"key":"10.1016\/j.eswa.2026.131501_bib0021","series-title":"International conference on machine learning","article-title":"Differentially private sharpness-aware training","author":"Park","year":"2023"},{"key":"10.1016\/j.eswa.2026.131501_bib0022","article-title":"Preserving differential privacy in convolutional deep belief networks","volume":"vol. 106","author":"Phan","year":"2017"},{"key":"10.1016\/j.eswa.2026.131501_bib0023","series-title":"Membership inference attacks on machine learning: A survey","volume":"vol. 54","author":"Rahman","year":"2022"},{"key":"10.1016\/j.eswa.2026.131501_bib0024","series-title":"Mastering the game of Go with deep neural networks and tree search","volume":"vol. 529","author":"Silver","year":"2016"},{"key":"10.1016\/j.eswa.2026.131501_bib0025","series-title":"Towards personalized federated learning","volume":"vol. 34","author":"Tan","year":"2022"},{"key":"10.1016\/j.eswa.2026.131501_bib0026","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v38i14.29451","article-title":"Dp-adambc: Your dp-adam is actually dp-sgd (unless you apply bias correction)","volume":"38","author":"Tang","year":"2024","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"10.1016\/j.eswa.2026.131501_bib0027","series-title":"Advances in neural information processing systems (neurips)","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.eswa.2026.131501_bib0028","article-title":"Empirical risk minimization in non-interactive local differential privacy revisited","volume":"vol. 32","author":"Wang","year":"2019"},{"key":"10.1016\/j.eswa.2026.131501_bib0029","series-title":"Technical Report","article-title":"Roughness index for loss landscapes of neural network models of partial differential equations","author":"Wu","year":"2024"},{"key":"10.1016\/j.eswa.2026.131501_bib0030","series-title":"Technical Report","article-title":"Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017"},{"key":"10.1016\/j.eswa.2026.131501_bib0031","series-title":"Technical Report","article-title":"Privacy-preserving Fine-Tuning of Localizable Language Models Using Adam Optimization with Adaptive Clipping","author":"Yang","year":"2025"},{"key":"10.1016\/j.eswa.2026.131501_bib0032","series-title":"Advances in neural information processing systems (neurips)","first-page":"2933","article-title":"Identifying and attacking the saddle point problem in high-dimensional non-convex optimization","author":"Yann","year":"2014"},{"key":"10.1016\/j.eswa.2026.131501_bib0033","article-title":"Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning","volume":"vol. 34","author":"Yu","year":"2021"},{"key":"10.1016\/j.eswa.2026.131501_bib0034","series-title":"A survey on differential privacy for unstructured data processing","volume":"vol. 10","author":"Zhao","year":"2024"},{"key":"10.1016\/j.eswa.2026.131501_bib0035","series-title":"Technical Report","article-title":"Federated learning with non-IID data","author":"Zhao","year":"2018"},{"issue":"37","key":"10.1016\/j.eswa.2026.131501_bib0036","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.ifacol.2026.01.003","article-title":"Roughness-Informed Machine Unlearning: A Call for Fractal and Fractional Calculi","volume":"59","author":"Partohaghighi","year":"2025","journal-title":"IFAC-PapersOnLine"},{"key":"10.1016\/j.eswa.2026.131501_bib0037","series-title":"2023 11th RSI International Conference on Robotics and Mechatronics (ICRoM)","first-page":"97","article-title":"Mobile Robot Path Planning Using Deep reinforcement learning","author":"Abedi","year":"2023"},{"issue":"6","key":"10.1016\/j.eswa.2026.131501_bib0038","doi-asserted-by":"crossref","first-page":"463","DOI":"10.1016\/j.jiixd.2025.09.001","article-title":"Roughness-informed machine learning - A call for fractal and fractional calculi","volume":"3","author":"Partohaghighi","year":"2025","journal-title":"Journal of Information and Intelligence"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426004148?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426004148?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T07:46:42Z","timestamp":1773215202000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426004148"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":38,"alternative-id":["S0957417426004148"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.131501","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Roughness-informed differential privacy","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.131501","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"131501"}}