{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:53:26Z","timestamp":1764356006460,"version":"3.46.0"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3635532","type":"journal-article","created":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T18:43:21Z","timestamp":1763664201000},"page":"198623-198648","source":"Crossref","is-referenced-by-count":0,"title":["Privacy Versus Utility in Federated Learning: An Experimental Analysis of Noise Injection Techniques"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7786-1946","authenticated-orcid":false,"given":"Neo R.","family":"Leope","sequence":"first","affiliation":[{"name":"Cyber Security Research Group (CySec), Department of Computer Science, EBIT Faculty, University of Pretoria, Pretoria, South Africa"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4683-2198","authenticated-orcid":false,"given":"Jan H. P.","family":"Eloff","sequence":"additional","affiliation":[{"name":"Cyber Security Research Group (CySec), Department of Computer Science, EBIT Faculty, University of Pretoria, Pretoria, South Africa"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8109-2979","authenticated-orcid":false,"given":"Moses T.","family":"Dlamini","sequence":"additional","affiliation":[{"name":"Cyber Security Research Group (CySec), Department of Computer Science, EBIT Faculty, University of Pretoria, Pretoria, South Africa"}]}],"member":"263","reference":[{"volume-title":"Cost of a Data Breach Report 2024","year":"2024","key":"ref1"},{"key":"ref2","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"Brendan McMahan","year":"2016","journal-title":"arXiv:1602.05629"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3233\/his-220006"},{"issue":"1","key":"ref4","first-page":"1","volume-title":"Advances and Open Problems in Federated Learning","volume":"14","author":"Kairouz"},{"key":"ref5","article-title":"How to backdoor federated learning","author":"Bagdasaryan","year":"2018","journal-title":"arXiv:1807.00459"},{"key":"ref6","first-page":"691","article-title":"Exploiting unintended feature leakage in collaborative learning","volume-title":"Proc. IEEE Symp. Secur. Privacy (SP)","author":"Melis"},{"key":"ref7","article-title":"IDLG: Improved deep leakage from gradients","author":"Zhao","year":"2020","journal-title":"arXiv:2001.02610"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"issue":"3","key":"ref9","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1561\/0400000042","article-title":"The algorithmic foundations of differential privacy","volume":"9","author":"Dwork","year":"2013","journal-title":"Found. Trends Theor. Comput. Sci."},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1016\/j.cose.2024.103922","article-title":"Protecting privacy and enhancing utility: A novel approach for personalized trajectory data publishing using noisy prefix tree","volume":"144","author":"Zhao","year":"2024","journal-title":"Comput. Secur."},{"key":"ref11","article-title":"Federated learning with non-IID data","author":"Zhao","year":"2018","journal-title":"arXiv:1806.00582"},{"key":"ref12","first-page":"5650","article-title":"Byzantine-robust distributed learning: Towards optimal statistical rates","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Yin"},{"key":"ref13","first-page":"118","article-title":"Machine learning with adversaries: Byzantine tolerant gradient descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Blanchard"},{"key":"ref14","article-title":"TrustFed: A reliable federated learning framework with malicious-attack resistance","author":"Su","year":"2023","journal-title":"arXiv:2312.04597"},{"key":"ref15","article-title":"G2uardFL: Safeguarding federated learning against backdoor attacks through attributed client graph clustering","author":"Yu","year":"2023","journal-title":"arXiv:2306.04984"},{"key":"ref16","first-page":"739","article-title":"Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning","volume-title":"Proc. IEEE Symp. Secur. Privacy (SP)","author":"Nasr"},{"key":"ref17","first-page":"14774","article-title":"Deep leakage from gradients","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhu"},{"key":"ref18","first-page":"111","article-title":"Differential privacy for federated learning: A survey of recent advances","volume":"14","author":"Zhu","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"ref19","article-title":"Practical secure aggregation for federated learning on user-held data","author":"Bonawitz","year":"2016","journal-title":"arXiv:1611.04482"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3338501.3357370"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3523273"},{"issue":"6","key":"ref22","doi-asserted-by":"crossref","first-page":"3282","DOI":"10.1109\/JBHI.2023.3304361","article-title":"A comprehensive privacy-preserving federated learning scheme with secure authentication and aggregation for Internet of Medical Things","volume":"28","author":"Liu","year":"2024","journal-title":"IEEE J. Biomed. Health Informat."},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tifs.2019.2939713"},{"key":"ref24","article-title":"Differentially private federated learning: A client level perspective","author":"Geyer","year":"2017","journal-title":"arXiv:1712.07557"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tce.2025.3601183"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i27.35005"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3504520"},{"issue":"4","key":"ref28","doi-asserted-by":"crossref","first-page":"3347","DOI":"10.1109\/TKDE.2021.3124599","article-title":"A survey on federated learning systems: Vision, hype and reality for data privacy and protection","volume":"35","author":"Li","year":"2023","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"1","key":"ref29","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s41666-020-00082-4","article-title":"Federated learning for healthcare informatics","volume":"5","author":"Xu","year":"2020","journal-title":"J. Healthcare Informat. Res."},{"issue":"6","key":"ref30","doi-asserted-by":"crossref","first-page":"473","DOI":"10.1038\/s42256-021-00337-8","article-title":"End-to-end privacy preserving deep learning on multi-institutional medical imaging","volume":"3","author":"Kaissis","year":"2021","journal-title":"Nature Mach. Intell."},{"issue":"7825","key":"ref31","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1038\/s41586-020-2649-2","article-title":"Array programming with NumPy","volume":"585","author":"Harris","year":"2020","journal-title":"Nature"},{"volume-title":"Faker: Python Package for Generating Fake Data","year":"2018","key":"ref32"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"807","DOI":"10.1109\/TIFS.2024.3518058","article-title":"Analyze and improve differentially private federated learning: A model robustness perspective","volume":"20","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Inf. Forensics Security"},{"key":"ref34","first-page":"1","article-title":"Privacy pinnacle: Improvising healthcare data security through federated learning and blockchain framework","volume-title":"Proc. 15th Int. Conf. Comput. Commun. Netw. Technol. (ICCCNT)","author":"Amreen"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"547","DOI":"10.1016\/j.future.2024.06.035","article-title":"Decentralized IoT data sharing: A blockchain-based federated learning approach with joint optimizations for efficiency and privacy","volume":"160","author":"Cheng","year":"2024","journal-title":"Future Gener. Comput. Syst."},{"key":"ref36","doi-asserted-by":"crossref","first-page":"88445","DOI":"10.1109\/ACCESS.2024.3418016","article-title":"Enhancing efficiency in privacy-preserving federated learning for healthcare: Adaptive Gaussian clipping with DFT aggregator","volume":"12","author":"Hidayat","year":"2024","journal-title":"IEEE Access"},{"issue":"1","key":"ref37","doi-asserted-by":"crossref","first-page":"767","DOI":"10.1109\/TWC.2024.3501297","article-title":"Communication-and-energy efficient over-the-air federated learning","volume":"24","author":"Liang","year":"2025","journal-title":"IEEE Trans. Wireless Commun."},{"issue":"3","key":"ref38","doi-asserted-by":"crossref","first-page":"3118","DOI":"10.1109\/JIOT.2024.3478208","article-title":"A lightweight and accuracy-lossless privacy-preserving method in federated learning","volume":"12","author":"Liu","year":"2025","journal-title":"IEEE Internet Things J."},{"key":"ref39","first-page":"1811","article-title":"Federated transfer learning based cooperative wideband spectrum sensing with model pruning","volume-title":"Proc. IEEE\/CIC Int. Conf. Commun. China (ICCC)","author":"Jia"},{"key":"ref40","first-page":"204","article-title":"Privacy preserving quantum search mechanism using Grover\u2019s algorithm","volume-title":"Proc. Int. Conf. Quantum Commun., Netw., Comput. (QCNC)","author":"Ju"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CSF.2018.00027"},{"key":"ref42","first-page":"3","article-title":"Membership inference attacks against machine learning models","volume-title":"Proc. IEEE Symp. Secur. Privacy (SP)","author":"Shokri"},{"key":"ref43","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1007\/11681878_14","article-title":"Calibrating noise to sensitivity in private data analysis","volume-title":"Theory of Cryptography (TCC 2006)","author":"Dwork","year":"2006"},{"key":"ref44","first-page":"1895","article-title":"Evaluating differentially private machine learning in practice","volume-title":"Proc. 28th USENIX Secur. Symp. (USENIX Secur.)","author":"Jayaraman"},{"issue":"6","key":"ref45","doi-asserted-by":"crossref","first-page":"975","DOI":"10.1109\/TBDATA.2023.3237397","article-title":"An experimental study of Byzantine-robust aggregation schemes in federated learning","volume":"10","author":"Li","year":"2024","journal-title":"IEEE Trans. Big Data"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3460427"},{"key":"ref47","article-title":"Gradient descent with linearly correlated noise: Theory and applications to differential privacy","author":"Koloskova","year":"2023","journal-title":"arXiv:2302.01463"},{"key":"ref48","first-page":"94","article-title":"Mechanism design via differential privacy","volume-title":"Proc. 48th Annu. IEEE Symp. Found. Comput. Sci. (FOCS)","author":"McSherry"},{"issue":"6","key":"ref49","first-page":"1","article-title":"Improved privacyutility trade-offs in federated learning","volume":"14","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11261524.pdf?arnumber=11261524","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:44:26Z","timestamp":1764355466000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11261524\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3635532","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}