{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T04:40:17Z","timestamp":1731127217777,"version":"3.28.0"},"reference-count":42,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Signal Processing"],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1016\/j.sigpro.2024.109742","type":"journal-article","created":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T20:12:45Z","timestamp":1729368765000},"page":"109742","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Adaptive compressed learning boosts both efficiency and utility of differentially private federated learning"],"prefix":"10.1016","volume":"227","author":[{"given":"Min","family":"Li","sequence":"first","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-6958-5807","authenticated-orcid":false,"given":"Di","family":"Xiao","sequence":"additional","affiliation":[]},{"given":"Lvjun","family":"Chen","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"3","key":"10.1016\/j.sigpro.2024.109742_b1","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1109\/MSP.2020.2975749","article-title":"Federated learning: Challenges, methods, and future directions","volume":"37","author":"Li","year":"2020","journal-title":"IEEE Signal Process. Mag."},{"issue":"3","key":"10.1016\/j.sigpro.2024.109742_b2","doi-asserted-by":"crossref","first-page":"2031","DOI":"10.1109\/COMST.2020.2986024","article-title":"Federated learning in mobile edge networks: A comprehensive survey","volume":"22","author":"Lim","year":"2020","journal-title":"IEEE Commun. Surv. Tutor."},{"issue":"1","key":"10.1016\/j.sigpro.2024.109742_b3","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1109\/MNET.011.2000295","article-title":"Toward resource-efficient federated learning in mobile edge computing","volume":"35","author":"Yu","year":"2021","journal-title":"IEEE Netw."},{"issue":"3","key":"10.1016\/j.sigpro.2024.109742_b4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3501296","article-title":"Federated learning for smart healthcare: A survey","volume":"55","author":"Nguyen","year":"2022","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.sigpro.2024.109742_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.comnet.2022.109048","article-title":"Fusion of federated learning and industrial Internet of Things: A survey","volume":"212","author":"Boobalan","year":"2022","journal-title":"Comput. Netw."},{"key":"10.1016\/j.sigpro.2024.109742_b6","doi-asserted-by":"crossref","first-page":"833","DOI":"10.1016\/j.ins.2023.03.033","article-title":"Federated learning in smart cities: Privacy and security survey","volume":"632","author":"Al-Huthaifi","year":"2023","journal-title":"Inform. Sci."},{"issue":"1","key":"10.1016\/j.sigpro.2024.109742_b7","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1109\/TIV.2023.3332675","article-title":"Federated learning for connected and automated vehicles: A survey of existing approaches and challenges","volume":"9","author":"Chellapandi","year":"2024","journal-title":"IEEE Trans. Int. Veh."},{"key":"10.1016\/j.sigpro.2024.109742_b8","series-title":"International Conference on Artificial Intelligence and Statistics","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"McMahan","year":"2017"},{"key":"10.1016\/j.sigpro.2024.109742_b9","series-title":"2019 IEEE Symposium on Security and Privacy","first-page":"691","article-title":"Exploiting unintended feature leakage in collaborative learning","author":"Melis","year":"2019"},{"unstructured":"L. Zhu, Z. Liu, S. Han, Deep leakage from gradients, in: Proceedings of the 33rd Conference on Neural Information Processing Systems, NeurIPS, 2019, pp. 14774\u201314784.","key":"10.1016\/j.sigpro.2024.109742_b10"},{"issue":"6","key":"10.1016\/j.sigpro.2024.109742_b11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3460427","article-title":"A comprehensive survey of privacy-preserving federated learning: A taxonomy, review, and future directions","volume":"54","author":"Yin","year":"2021","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.sigpro.2024.109742_b12","doi-asserted-by":"crossref","first-page":"619","DOI":"10.1016\/j.future.2020.10.007","article-title":"A survey on security and privacy of federated learning","volume":"115","author":"Mothukuri","year":"2021","journal-title":"Future Gener. Comput. Syst."},{"key":"10.1016\/j.sigpro.2024.109742_b13","doi-asserted-by":"crossref","DOI":"10.1109\/TNSM.2024.3393969","article-title":"A differentially privacy assisted federated learning scheme to preserve data privacy for IoMT applications","author":"Barnawi","year":"2024","journal-title":"IEEE Trans. Netw. Serv. Manag."},{"key":"10.1016\/j.sigpro.2024.109742_b14","series-title":"Proceedings of 2016 ACM SIGSAC Conference on Computer and Communications Security","first-page":"308","article-title":"Deep learning with differential privacy","author":"Abadi","year":"2016"},{"issue":"1","key":"10.1016\/j.sigpro.2024.109742_b15","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1109\/TDSC.2017.2734664","article-title":"Sensitivity analysis for non-interactive differential privacy: Bounds and efficient algorithms","volume":"17","author":"Inan","year":"2020","journal-title":"IEEE Trans. Dependable Secure Comput."},{"key":"10.1016\/j.sigpro.2024.109742_b16","series-title":"Proceedings of 2018 International Conference on Management of Data","first-page":"1655","article-title":"Privacy at scale: Local differential privacy in practice","author":"Cormode","year":"2018"},{"issue":"6","key":"10.1016\/j.sigpro.2024.109742_b17","doi-asserted-by":"crossref","first-page":"2824","DOI":"10.1109\/TKDE.2020.3014246","article-title":"More than privacy: Applying differential privacy in key areas of artificial intelligence","volume":"34","author":"Zhu","year":"2022","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.sigpro.2024.109742_b18","doi-asserted-by":"crossref","first-page":"408","DOI":"10.1016\/j.future.2023.06.010","article-title":"Differential privacy in deep learning: Privacy and beyond","volume":"148","author":"Wang","year":"2023","journal-title":"Future Gener. Comput. Syst."},{"key":"10.1016\/j.sigpro.2024.109742_b19","doi-asserted-by":"crossref","first-page":"1113","DOI":"10.1613\/jair.1.14649","article-title":"How to DP-fy ML: A practical guide to machine learning with differential privacy","volume":"77","author":"Ponomareva","year":"2023","journal-title":"J. Artificial Intelligence Res."},{"issue":"3","key":"10.1016\/j.sigpro.2024.109742_b20","first-page":"1","article-title":"Deep learning with Gaussian differential privacy","volume":"2","author":"Bu","year":"2020","journal-title":"Harv. Data Sci. Rev."},{"issue":"1","key":"10.1016\/j.sigpro.2024.109742_b21","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1111\/rssb.12454","article-title":"Gaussian differential privacy","volume":"84","author":"Dong","year":"2022","journal-title":"J. R. Stat. Soc. Ser. B Stat. Methodol."},{"key":"10.1016\/j.sigpro.2024.109742_b22","series-title":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","first-page":"505","article-title":"Connecting low-loss subspace for personalized federated learning","author":"Hahn","year":"2022"},{"issue":"2","key":"10.1016\/j.sigpro.2024.109742_b23","doi-asserted-by":"crossref","first-page":"1558","DOI":"10.1109\/TNSM.2023.3263831","article-title":"Communication-efficient personalized federated meta-learning in edge networks","volume":"20","author":"Yu","year":"2023","journal-title":"IEEE Trans. Netw. Serv. Manag."},{"issue":"2","key":"10.1016\/j.sigpro.2024.109742_b24","doi-asserted-by":"crossref","first-page":"1517","DOI":"10.1109\/TNSM.2023.3278023","article-title":"FedCLS: Class-aware federated learning in a heterogeneous environment","volume":"20","author":"Bhatti","year":"2023","journal-title":"IEEE Trans. Netw. Serv. Manag."},{"key":"10.1016\/j.sigpro.2024.109742_b25","series-title":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"3441","article-title":"Finding needles in compressed haystacks","author":"Calderbank","year":"2012"},{"key":"10.1016\/j.sigpro.2024.109742_b26","series-title":"2016 IEEE International Conference on Image Processing","first-page":"1913","article-title":"Direct inference on compressive measurements using convolutional neural networks","author":"Lohit","year":"2016"},{"issue":"4","key":"10.1016\/j.sigpro.2024.109742_b27","doi-asserted-by":"crossref","first-page":"772","DOI":"10.1109\/TPAMI.2015.2469288","article-title":"Reconstruction-free action inference from compressive imagers","volume":"38","author":"Kulkarni","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"10.1016\/j.sigpro.2024.109742_b28","doi-asserted-by":"crossref","first-page":"1512","DOI":"10.1109\/TNNLS.2020.2984831","article-title":"Multilinear compressive learning","volume":"32","author":"Tran","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"4","key":"10.1016\/j.sigpro.2024.109742_b29","doi-asserted-by":"crossref","first-page":"801","DOI":"10.1109\/TBCAS.2018.2828031","article-title":"Low-complexity privacy-preserving compressive analysis using subspace-based dictionary for ECG telemonitoring system","volume":"12","author":"Chou","year":"2018","journal-title":"IEEE Trans. Biomed. Circuits Syst."},{"issue":"4","key":"10.1016\/j.sigpro.2024.109742_b30","first-page":"5236","article-title":"TransCL: Transformer makes strong and flexible compressive learning","volume":"45","author":"Mou","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"unstructured":"Y. Yang, B. Hui, H. Yuan, N. Gong, Y. Cao, PRIVATEFL: Accurate, differentially private federated learning via personalized data transformation, in: 32nd USENIX Security Symposium (USENIX Security), 2023, pp. 1595\u20131611.","key":"10.1016\/j.sigpro.2024.109742_b31"},{"issue":"4","key":"10.1016\/j.sigpro.2024.109742_b32","doi-asserted-by":"crossref","first-page":"1289","DOI":"10.1109\/TIT.2006.871582","article-title":"Compressed sensing","volume":"52","author":"Donoho","year":"2006","journal-title":"IEEE Trans. Inform. Theory"},{"issue":"3","key":"10.1016\/j.sigpro.2024.109742_b33","doi-asserted-by":"crossref","first-page":"476","DOI":"10.1109\/TDSC.2018.2821140","article-title":"Detecting fault injection attacks based on compressed sensing and integer linear programming","volume":"16","author":"Li","year":"2019","journal-title":"IEEE Trans. Dependable Secure Comput."},{"issue":"14","key":"10.1016\/j.sigpro.2024.109742_b34","doi-asserted-by":"crossref","first-page":"3632","DOI":"10.1109\/TSP.2017.2699639","article-title":"Joint sensing matrix and sparsifying dictionary optimization for tensor compressive sensing","volume":"65","author":"Ding","year":"2017","journal-title":"IEEE Trans. Signal Process."},{"issue":"1","key":"10.1016\/j.sigpro.2024.109742_b35","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1109\/TSP.2013.2284762","article-title":"Permutation meets parallel compressed sensing: How to relax restricted isometry property for 2D sparse signals","volume":"62","author":"Fang","year":"2014","journal-title":"IEEE Trans. Signal Process."},{"issue":"8","key":"10.1016\/j.sigpro.2024.109742_b36","doi-asserted-by":"crossref","first-page":"1725","DOI":"10.1109\/LCOMM.2022.3180113","article-title":"Communication-efficient and Byzantine-robust differentially private federated learning","volume":"26","author":"Li","year":"2022","journal-title":"IEEE Commun. Lett."},{"key":"10.1016\/j.sigpro.2024.109742_b37","series-title":"Proceedings of the 5th Symposium on Electronic Imaging: Computational Imaging","first-page":"142","article-title":"The smashed filter for compressive classification and target recognition","author":"Davenport","year":"2007"},{"issue":"9","key":"10.1016\/j.sigpro.2024.109742_b38","doi-asserted-by":"crossref","first-page":"3388","DOI":"10.1109\/TMC.2021.3056991","article-title":"User-level privacy-preserving federated learning: Analysis and performance optimization","volume":"21","author":"Wei","year":"2022","journal-title":"IEEE Trans. Mob. Comput."},{"key":"10.1016\/j.sigpro.2024.109742_b39","doi-asserted-by":"crossref","first-page":"3454","DOI":"10.1109\/TIFS.2020.2988575","article-title":"Federated learning with differential privacy: Algorithms and performance analysis","volume":"15","author":"Wei","year":"2020","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"10.1016\/j.sigpro.2024.109742_b40","doi-asserted-by":"crossref","first-page":"4488","DOI":"10.1109\/TIFS.2023.3293417","article-title":"Personalized federated learning with differential privacy and convergence guarantee","volume":"18","author":"Wei","year":"2023","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"10.1016\/j.sigpro.2024.109742_b41","series-title":"Proceedings of the 38th International Conference on Machine Learning","first-page":"21","article-title":"Debiasing model updates for improving personalized federated training","author":"Acar","year":"2021"},{"key":"10.1016\/j.sigpro.2024.109742_b42","series-title":"Proceedings of the 24th International Conference on Artificial Intelligence and Statistics","first-page":"2251","article-title":"Federated f-differential privacy","author":"Zheng","year":"2021"}],"container-title":["Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0165168424003621?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0165168424003621?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T03:43:59Z","timestamp":1731123839000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0165168424003621"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":42,"alternative-id":["S0165168424003621"],"URL":"https:\/\/doi.org\/10.1016\/j.sigpro.2024.109742","relation":{},"ISSN":["0165-1684"],"issn-type":[{"type":"print","value":"0165-1684"}],"subject":[],"published":{"date-parts":[[2025,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Adaptive compressed learning boosts both efficiency and utility of differentially private federated learning","name":"articletitle","label":"Article Title"},{"value":"Signal Processing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.sigpro.2024.109742","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 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":"109742"}}