{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T04:04:38Z","timestamp":1784952278290,"version":"3.55.0"},"reference-count":105,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"European Union-NextGenerationEU (EU-NGEU), respectively","award":["PE00000014"],"award-info":[{"award-number":["PE00000014"]}]},{"name":"European Union-NextGenerationEU (EU-NGEU), respectively","award":["PE0000001"],"award-info":[{"award-number":["PE0000001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tnnls.2024.3478334","type":"journal-article","created":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T13:26:22Z","timestamp":1729862782000},"page":"11697-11717","source":"Crossref","is-referenced-by-count":60,"title":["Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metrics"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2820-5978","authenticated-orcid":false,"given":"Nicol\u00f2","family":"Romandini","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering (DISI), University of Bologna, Bologna, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8161-1070","authenticated-orcid":false,"given":"Alessio","family":"Mora","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering (DISI), University of Bologna, Bologna, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8949-2221","authenticated-orcid":false,"given":"Carlo","family":"Mazzocca","sequence":"additional","affiliation":[{"name":"Department of Computer and Electrical Engineering and Applied Mathematics (DIEM), University of Salerno, Fisciano, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3687-0361","authenticated-orcid":false,"given":"Rebecca","family":"Montanari","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering (DISI), University of Bologna, Bologna, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0992-7948","authenticated-orcid":false,"given":"Paolo","family":"Bellavista","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering (DISI), University of Bologna, Bologna, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2507157.2507163"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532027"},{"key":"ref3","volume-title":"Facebook-Cambridge Analytica Data Scandal","year":"2023"},{"key":"ref4","volume-title":"Complete Guide to General Data Protection Regulation Compliance","author":"Union","year":"2023"},{"key":"ref5","volume-title":"California Consumer Privacy Act (CCPA)","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3603620"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2015.35"},{"key":"ref8","first-page":"14747","article-title":"Deep leakage from gradients","volume-title":"Proc. 33rd Conf. Neural Inf. Process. Syst.","author":"Zhu"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.41"},{"key":"ref10","article-title":"Learn to forget: Machine unlearning via neuron masking","author":"Liu","year":"2020","journal-title":"arXiv:2003.10933"},{"key":"ref11","article-title":"A survey of federated unlearning: A taxonomy, challenges and future directions","author":"Zhao","year":"2023","journal-title":"arXiv:2310.19218"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.004.2300056"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3679014"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-023-01767-4"},{"key":"ref15","article-title":"Learn to unlearn: A survey on machine unlearning","author":"Qu","year":"2023","journal-title":"arXiv:2305.07512"},{"key":"ref16","article-title":"A survey of machine unlearning","author":"Tam Nguyen","year":"2022","journal-title":"arXiv:2209.02299"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00932"},{"key":"ref18","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. 20th Int. Conf. Artif. Intell. Statist.","volume":"54","author":"McMahan"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3429252"},{"key":"ref20","article-title":"Adaptive federated optimization","author":"Reddi","year":"2020","journal-title":"arXiv:2003.00295"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00029"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/sp.2019.00065"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.12.004"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11651"},{"key":"ref25","article-title":"Re-weighted softmax cross-entropy to control forgetting in federated learning","author":"Legate","year":"2023","journal-title":"arXiv:2304.05260"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20050-2_38"},{"key":"ref27","first-page":"38461","article-title":"Preservation of the global knowledge by not-true distillation in federated learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref28","article-title":"VeriFi: Towards verifiable federated unlearning","author":"Gao","year":"2022","journal-title":"arXiv:2205.12709"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-5906-5_752"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1561\/9781601988195"},{"key":"ref31","article-title":"Learning differentially private recurrent language models","author":"McMahan","year":"2017","journal-title":"arXiv:1710.06963"},{"key":"ref32","article-title":"Differentially private federated learning: A client level perspective","author":"Geyer","year":"2017","journal-title":"arXiv:1712.07557"},{"key":"ref33","first-page":"15453","article-title":"Differential privacy has disparate impact on model accuracy","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"32","author":"Bagdasaryan"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.001.2200198"},{"key":"ref35","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Adv. Neural Inf. Process. Sys. (NIPS)","volume":"34","author":"Xie"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3338501.3357370"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/tbdata.2022.3208736"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25879"},{"key":"ref39","article-title":"Measuring the effects of non-identical data distribution for federated visual classification","author":"Hsu","year":"2019","journal-title":"arXiv:1909.06335"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00077"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9602"},{"key":"ref42","first-page":"1885","article-title":"Understanding black-box predictions via influence functions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Koh"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2024.3382726"},{"key":"ref44","article-title":"BadNets: Identifying vulnerabilities in the machine learning model supply chain","author":"Gu","year":"2017","journal-title":"arXiv:1708.06733"},{"key":"ref45","first-page":"2938","article-title":"How to backdoor federated learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Bagdasaryan"},{"key":"ref46","first-page":"1605","article-title":"Local model poisoning attacks to \\Byzantine-robust\\ federated learning","volume-title":"Proc. 29th USENIX Secur. Symp. (USENIX Secur.)","author":"Fang"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00085"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CSF.2018.00027"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/532"},{"key":"ref50","article-title":"Federated unlearning: How to efficiently erase a client in FL?","author":"Halimi","year":"2022","journal-title":"arXiv:2207.05521"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM53939.2023.10229075"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796721"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512222"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/IWQOS52092.2021.9521274"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC51858.2021.9593225"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3321594"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3570463"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/SP46215.2023.10179336"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2023.3343117"},{"key":"ref60","article-title":"Federated unlearning with knowledge distillation","author":"Wu","year":"2022","journal-title":"arXiv:2201.09441"},{"key":"ref61","article-title":"Heterogeneous decentralized machine unlearning with seed model distillation","author":"Ye","year":"2023","journal-title":"arXiv:2308.13269"},{"key":"ref62","article-title":"Subspace based federated unlearning","author":"Li","year":"2023","journal-title":"arXiv:2302.12448"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/tai.2024.3465441"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/DSLW53931.2022.9820602"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2022.3223655"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3579856.3590327"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3297905"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2021.3104842"},{"key":"ref69","article-title":"Machine unlearning of federated clusters","author":"Pan","year":"2022","journal-title":"arXiv:2210.16424"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.14778\/3641204.3641220"},{"key":"ref71","article-title":"QuickDrop: Efficient federated unlearning by integrated dataset distillation","author":"Dhasade","year":"2023","journal-title":"arXiv:2311.15603"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2300272"},{"key":"ref73","article-title":"Forgettable federated linear learning with certified data removal","author":"Jin","year":"2023","journal-title":"arXiv:2306.02216"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3310049"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM58522.2023.00188"},{"key":"ref76","first-page":"4241","article-title":"Fast federated machine unlearning with nonlinear functional theory","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","volume":"202","author":"Che"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583305"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.2307\/2006193"},{"key":"ref79","article-title":"Knowledge distillation for federated learning: A practical guide","author":"Mora","year":"2022","journal-title":"arXiv:2211.04742"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1016\/0168-9002(95)01478-0"},{"key":"ref81","first-page":"2378","article-title":"Stein variational gradient descent: A general purpose Bayesian inference algorithm","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Liu"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2022.3168490"},{"key":"ref83","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/741"},{"key":"ref85","first-page":"13433","article-title":"Prompt certified machine unlearning with randomized gradient smoothing and quantization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Zhang"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3070843"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482252"},{"key":"ref88","article-title":"LEAF: A benchmark for federated settings","author":"Caldas","year":"2018","journal-title":"arXiv:1812.01097"},{"key":"ref89","volume-title":"Tensorflow Federated","year":"2023"},{"key":"ref90","article-title":"Flower: A friendly federated learning research framework","author":"Beutel","year":"2020","journal-title":"arXiv:2007.14390"},{"key":"ref91","volume-title":"Flower Datasets","year":"2023"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1145\/3565287.3610269"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12143182"},{"key":"ref94","article-title":"Multi-participant multi-class vertical federated learning","author":"Feng","year":"2020","journal-title":"arXiv:2001.11154"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3282899"},{"key":"ref96","first-page":"11220","article-title":"Federated Reconstruction: Partially Local Federated Learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Singhal"},{"key":"ref97","article-title":"Practical attribute reconstruction attack against federated learning","author":"Chen","year":"2022","journal-title":"IEEE Trans. Big Data"},{"key":"ref98","first-page":"16937","article-title":"Inverting gradients\u2014How easy is it to break privacy in federated learning?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Geiping"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1145\/3214303"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1145\/3383455.3422562"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/SEC54971.2022.00049"},{"key":"ref102","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref103","article-title":"Caltech-UCSD birds 200","author":"Welinder","year":"2010"},{"key":"ref104","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01776"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11073756\/10736348.pdf?arnumber=10736348","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,9]],"date-time":"2025-07-09T23:21:00Z","timestamp":1752103260000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10736348\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":105,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3478334","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}