{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T15:06:09Z","timestamp":1789225569151,"version":"build-2803163510"},"reference-count":53,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100011246","name":"State Key Laboratory of Novel Software Technology","doi-asserted-by":"publisher","award":["KFKT2025B03"],"award-info":[{"award-number":["KFKT2025B03"]}],"id":[{"id":"10.13039\/501100011246","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013804","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013804","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017534","name":"Project 333 of Jiangsu Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100017534","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["B250201047"],"award-info":[{"award-number":["B250201047"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Reliability Engineering &amp; System Safety"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.ress.2026.113281","type":"journal-article","created":{"date-parts":[[2026,8,15]],"date-time":"2026-08-15T14:57:56Z","timestamp":1786805876000},"page":"113281","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"P6","title":["Spectrum-feature-aware robust federated learning for malicious client detection"],"prefix":"10.1016","volume":"277","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7797-0094","authenticated-orcid":false,"given":"Yang","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanshuo","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6082-5955","authenticated-orcid":false,"given":"Xue","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7375-0393","authenticated-orcid":false,"given":"Siguang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.ress.2026.113281_b1","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1016\/j.eng.2023.10.006","article-title":"Secure federated evolutionary optimization\u2014A survey","volume":"34","author":"Liu","year":"2024","journal-title":"Engineering"},{"key":"10.1016\/j.ress.2026.113281_b2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.ress.2025.111444","article-title":"Unsupervised cyberattack detection in smart grids: A novel approach integrating horizontal federated learning for the control center and substations","volume":"264","author":"Zheng","year":"2025","journal-title":"Reliab Eng Syst Saf"},{"key":"10.1016\/j.ress.2026.113281_b3","first-page":"1","article-title":"Label synchronization strategies for hybrid federated learning","volume":"256","author":"Roseroa","year":"2025","journal-title":"Reliab Eng Syst Saf"},{"key":"10.1016\/j.ress.2026.113281_b4","unstructured":"Bagdasaryan E, Veit A, Hua Y, et al. How to backdoor federated learning. In: Proc. int. conf. artif. intell. stat.. AISTATS, 2020, p. 2938\u201348."},{"key":"10.1016\/j.ress.2026.113281_b5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.media.2023.102965","article-title":"Backdoor attack and defense in federated generative adversarial network-based medical image synthesis","volume":"90","author":"Jin","year":"2023","journal-title":"Med Image Anal"},{"key":"10.1016\/j.ress.2026.113281_b6","series-title":"2025 Data breach investigations report","author":"Hylender","year":"2025"},{"key":"10.1016\/j.ress.2026.113281_b7","series-title":"Cost of a data breach report 2025","author":"Kessem","year":"2025"},{"issue":"6","key":"10.1016\/j.ress.2026.113281_b8","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"},{"issue":"8","key":"10.1016\/j.ress.2026.113281_b9","doi-asserted-by":"crossref","first-page":"14017","DOI":"10.1109\/JIOT.2023.3339495","article-title":"Compressed sensing-based practical and efficient privacy-preserving federated learning","volume":"11","author":"Chen","year":"2024","journal-title":"IEEE Internet Things J"},{"issue":"3","key":"10.1016\/j.ress.2026.113281_b10","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1109\/TSUSC.2023.3341836","article-title":"Amplitude-aligned personalization and robust aggregation for federated learning","volume":"9","author":"Jiang","year":"2024","journal-title":"IEEE Trans Sust. Comp"},{"key":"10.1016\/j.ress.2026.113281_b11","unstructured":"Huang W, Shi Z, Ye M, et al. Self-driven entropy aggregation for byzantine-robust heterogeneous federated learning. In: Proc. int. conf. mach. learn.. ICML, 2024, p. 20096\u2013110."},{"key":"10.1016\/j.ress.2026.113281_b12","doi-asserted-by":"crossref","unstructured":"Fang M, Zhang Z, Hairi, et al. Byzantine-robust decentralized federated learning. In: Proc. ACM SIGSAC conf. comput. commun. secur.. CCS, 2024, p. 2874\u201388.","DOI":"10.1145\/3658644.3670307"},{"key":"10.1016\/j.ress.2026.113281_b13","unstructured":"Xie Y, Fang M, Gong N. FedREDefense: Defending against model poisoning attacks for federated learning using model update reconstruction error. In: Proc. int. conf. mach. learn.. ICML, 2024, p. 54460\u201374."},{"issue":"1","key":"10.1016\/j.ress.2026.113281_b14","first-page":"1","article-title":"Identifying alternately poisoning attacks in federated learning online using trajectory anomaly detection method","volume":"14","author":"Ding","year":"2024","journal-title":"Sci Rep"},{"issue":"10","key":"10.1016\/j.ress.2026.113281_b15","doi-asserted-by":"crossref","first-page":"2848","DOI":"10.1109\/TAI.2025.3556092","article-title":"Malicious clients and contribution co-aware federated unlearning","volume":"6","author":"Wang","year":"2025","journal-title":"IEEE. Trans Artif Intell"},{"issue":"1","key":"10.1016\/j.ress.2026.113281_b16","first-page":"239","article-title":"Defending federated learning system from poisoning attacks via efficient unlearning","volume":"83","author":"Cai","year":"2025","journal-title":"Comput Mater Contin"},{"key":"10.1016\/j.ress.2026.113281_b17","doi-asserted-by":"crossref","unstructured":"Ding B, Yang P, Huang S. FedDLAD: A federated learning dual-layer anomaly detection framework for enhancing resilience against backdoor attacks. In: Int. joint conf. artif. intell.. IJCAI, 2025, p. 5021\u20139.","DOI":"10.24963\/ijcai.2025\/559"},{"key":"10.1016\/j.ress.2026.113281_b18","series-title":"FLAegis: A two-layer defense framework for federated learning against poisoning attacks","author":"Campos","year":"2025"},{"key":"10.1016\/j.ress.2026.113281_b19","doi-asserted-by":"crossref","unstructured":"Yang Y, Li Q, Nie C, et al. Breaking state-of-the-art poisoning defenses to federated learning: An optimization-based attack framework. In: Proc. int. conf. inf. knowledge manage. CIKM, 2024, p. 2930\u20139.","DOI":"10.1145\/3627673.3679566"},{"key":"10.1016\/j.ress.2026.113281_b20","doi-asserted-by":"crossref","unstructured":"Huang S, Li Y, Chen C, et al. Multi-metrics adaptively identifies backdoors in Federated learning. In: Proc. IEEE int. conf. comput vision. ICCV, 2023, p. 4629\u201339.","DOI":"10.1109\/ICCV51070.2023.00429"},{"key":"10.1016\/j.ress.2026.113281_b21","doi-asserted-by":"crossref","unstructured":"Rieger P, Krau\u00df T, Miettinen M, et al. CrowdGuard: Federated backdoor detection in federated learning. In: Proc. annu. netw. distrib. syst. secur. symp.. NDSS, 2024, p. 1\u201318.","DOI":"10.14722\/ndss.2024.23233"},{"issue":"11","key":"10.1016\/j.ress.2026.113281_b22","doi-asserted-by":"crossref","first-page":"24134","DOI":"10.1109\/JIOT.2026.3671698","article-title":"Wavelet scattering transform and fourier representation for offline detection of malicious clients in federated learning","volume":"13","author":"Licciardi","year":"2026","journal-title":"IEEE Internet Things J"},{"key":"10.1016\/j.ress.2026.113281_b23","doi-asserted-by":"crossref","unstructured":"Zhang T, Chen B, Zhang J, et al. Detecting stealthy backdoor attacks in federated learning via wavelet analysis on dynamic dimensions. In: Proc. int. conf. inf. secur. cryptol.. INSCRYPT, 2026, p. 250\u201369.","DOI":"10.1007\/978-981-95-6209-1_14"},{"key":"10.1016\/j.ress.2026.113281_b24","doi-asserted-by":"crossref","unstructured":"Yan X, Wu L, Zhang Z, et al. FedBAP: Backdoor defense via benign adversarial perturbation in federated learning. In: Proc. ACM int. conf. multimedia, co-located with MM. MM, 2025, p. 11947\u201355.","DOI":"10.1145\/3746027.3754814"},{"key":"10.1016\/j.ress.2026.113281_b25","unstructured":"Blanchard P, Mhamdi EM El, Guerraoui R, et al. Machine learning with adversaries: Byzantine tolerant gradient descent. In: Proc. adv. neural inf. proces. syst.. NeurIPS, 2017, p. 119\u201329."},{"key":"10.1016\/j.ress.2026.113281_b26","unstructured":"Mhamdi EM El, Guerraoui R, Rouault S. The hidden vulnerability of distributed learning in byzantium. In: Proc. int. conf. mach. learn.. ICML, 2018, p. 3521\u201330."},{"key":"10.1016\/j.ress.2026.113281_b27","unstructured":"Yin D, Chen Y, Ramchandran K, et al. Byzantine-robust distributed learning: Towards optimal statistical rates. In: Proc. int. conf. mach. learn.. ICML, 2018, p. 8947\u201356."},{"key":"10.1016\/j.ress.2026.113281_b28","doi-asserted-by":"crossref","first-page":"1142","DOI":"10.1109\/TSP.2022.3153135","article-title":"Robust aggregation for federated learning","volume":"70","author":"Pillutla","year":"2022","journal-title":"IEEE Trans Signal Process"},{"key":"10.1016\/j.ress.2026.113281_b29","unstructured":"Yaldiz DN, Zhang T, Avestimehr S. Secure federated learning against model poisoning attacks via client filtering. In: Proc. int. conf. learn. represent.. ICLR, 2023, p. 1\u201310."},{"key":"10.1016\/j.ress.2026.113281_b30","series-title":"SoK: Benchmarking poisoning attacks and defenses in federated learning","author":"Zhang","year":"2025"},{"key":"10.1016\/j.ress.2026.113281_b31","doi-asserted-by":"crossref","unstructured":"Cao X, Fang M, Liu J, et al. FLTrust: Byzantine-robust federated learning via trust bootstrapping. In: Proc. annu. netw. distrib. syst. secur. symp.. NDSS, 2021, p. 1\u201318.","DOI":"10.14722\/ndss.2021.24434"},{"key":"10.1016\/j.ress.2026.113281_b32","unstructured":"Nguyen TD, Rieger P, Chen H, et al. FLAME: Taming backdoors in federated learning. In: Proc. proc. USeNIX secur. symp., security. USENIX Security, 2022, p. 1415\u201332."},{"key":"10.1016\/j.ress.2026.113281_b33","doi-asserted-by":"crossref","unstructured":"Zhang Z, Cao X, Jia J, et al. FLDetector: Defending federated learning against model poisoning attacks via detecting malicious clients. In: Proc. ACM SIGKDD int. conf. knowl. discov. data min.. KDD, 2022, p. 2545\u201355.","DOI":"10.1145\/3534678.3539231"},{"issue":"6","key":"10.1016\/j.ress.2026.113281_b34","doi-asserted-by":"crossref","first-page":"5259","DOI":"10.1109\/TDSC.2024.3372634","article-title":"Feddmc: Efficient and precise malicious client detection for robust federated learning","volume":"21","author":"Mu","year":"2024","journal-title":"IEEE Trans Dependable Secur Comput"},{"key":"10.1016\/j.ress.2026.113281_b35","doi-asserted-by":"crossref","unstructured":"Dou Z, Wang J, Liu Z, et al. Toward malicious clients detection in federated learning. In: Proc. ACM SIGSAC conf. comput. commun. secur.. CCS, 2025, p. 456\u201372.","DOI":"10.1145\/3708821.3736194"},{"key":"10.1016\/j.ress.2026.113281_b36","doi-asserted-by":"crossref","unstructured":"Kavuri LA, Mhatre A, Nair AK, et al. SecureFed: A two-phase framework for detecting malicious clients in federated learning. In: Proc. IEEE int. conf. inf. reuse integr. data sci.. IRI, 2025, p. 190\u20135.","DOI":"10.1109\/IRI66576.2025.00043"},{"key":"10.1016\/j.ress.2026.113281_b37","first-page":"1","article-title":"M3D-FL: Multi-layer malicious model detection for federated learning in IoT networks","volume":"154","author":"Atia","year":"2025","journal-title":"Comput Secur"},{"key":"10.1016\/j.ress.2026.113281_b38","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.comnet.2025.111442","article-title":"Flcom: Robust federated learning against strong model poisoning attacks","volume":"269","author":"Li","year":"2025","journal-title":"Comput Networks."},{"key":"10.1016\/j.ress.2026.113281_b39","doi-asserted-by":"crossref","unstructured":"Xie Y, Fang M, Gong NZ. Model poisoning attacks to federated learning via multi-round consistency. In: Proc. IEEE conf. comput. vis. pattern recognit.. CVPR, 2025, p. 15454\u201363.","DOI":"10.1109\/CVPR52734.2025.01440"},{"key":"10.1016\/j.ress.2026.113281_b40","doi-asserted-by":"crossref","unstructured":"Shejwalkar V, Houmansadr A. Manipulating the byzantine: optimizing model poisoning attacks and defenses for federated learning. In: Proc. annu. netw. distrib. syst. secur. symp.. NDSS, 2021, p. 1\u201318.","DOI":"10.14722\/ndss.2021.24498"},{"key":"10.1016\/j.ress.2026.113281_b41","doi-asserted-by":"crossref","unstructured":"Fereidooni H, Pegoraro A, Rieger P, et al. FreqFed: a frequency analysis-based approach for mitigating poisoning attacks in federated learning. In: Proc. annu. netw. distrib. syst. secur. symp.. NDSS, 2024, p. 1\u201316.","DOI":"10.14722\/ndss.2024.24620"},{"issue":"6","key":"10.1016\/j.ress.2026.113281_b42","doi-asserted-by":"crossref","first-page":"3750","DOI":"10.1007\/s12083-024-01794-9","article-title":"DWAMA: Dynamic weight-adjusted mahalanobis defense algorithm for mitigating poisoning attacks in federated learning","volume":"17","author":"Zhang","year":"2024","journal-title":"Peer-To-Peer Netw Appl"},{"key":"10.1016\/j.ress.2026.113281_b43","doi-asserted-by":"crossref","unstructured":"Huang W, Ye M, Shi Z, et al. Parameter disparities dissection for backdoor defense in heterogeneous federated learning. In: Proc. adv. neural inf. proces. syst.. NeurIPS, 2024, p. 1\u201323.","DOI":"10.52202\/079017-3843"},{"key":"10.1016\/j.ress.2026.113281_b44","doi-asserted-by":"crossref","unstructured":"Xu R, Gao S, Li C, et al. Dual defense: Enhancing privacy and mitigating poisoning attacks in federated learning. In: Proc. adv. neural inf. proces. syst.. NeurIPS, 2024, p. 1\u201323.","DOI":"10.52202\/079017-2253"},{"key":"10.1016\/j.ress.2026.113281_b45","doi-asserted-by":"crossref","first-page":"2577","DOI":"10.1109\/TIFS.2025.3539964","article-title":"FedGT: Identification of malicious clients in federated learning with secure aggregation","volume":"20","author":"Xhemrishi","year":"2025","journal-title":"IEEE Trans Inf Forensics Secur"},{"key":"10.1016\/j.ress.2026.113281_b46","doi-asserted-by":"crossref","first-page":"9100","DOI":"10.1109\/TIFS.2024.3451359","article-title":"Fedpta: Prior-based tensor approximation for detecting malicious clients in federated learning","volume":"19","author":"Mu","year":"2024","journal-title":"IEEE Trans Inf Forensics Secur"},{"key":"10.1016\/j.ress.2026.113281_b47","doi-asserted-by":"crossref","first-page":"6027","DOI":"10.1109\/TNSE.2026.3654756","article-title":"Malicious or benign?\u201d: Enhancing the contribution of model updates in byzantine-robust heterogeneous federated learning","volume":"13","author":"Zhang","year":"2026","journal-title":"IEEE Trans Netw Sci Eng"},{"issue":"1","key":"10.1016\/j.ress.2026.113281_b48","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1109\/T-C.1974.223784","article-title":"Discrete cosine transform","volume":"C-23","author":"Ahmed","year":"1974","journal-title":"IEEE Trans Comput"},{"issue":"6","key":"10.1016\/j.ress.2026.113281_b49","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1109\/MSP.2012.2211477","article-title":"The mnist database of handwritten digit images for machine learning research","volume":"29","author":"Deng","year":"2012","journal-title":"IEEE Signal Process Mag"},{"key":"10.1016\/j.ress.2026.113281_b50","doi-asserted-by":"crossref","unstructured":"Abouelnaga Y, Ali OS, Rady H, et al. CIFAR-10: KNNbased ensemble of classifiers. In: Proc. IEEE int. conf. comput. sci. comput. intell.. CSCI, 2016, p. 1192\u20135.","DOI":"10.1109\/CSCI.2016.0225"},{"key":"10.1016\/j.ress.2026.113281_b51","doi-asserted-by":"crossref","unstructured":"Stallkamp J, Schlipsing M, Salmen J, et al. The German traffic sign recognition benchmark: A multi-class classification competition. In: Proc. int. jt. conf. neural networks. IJCNN, 2011, p. 1453\u201360.","DOI":"10.1109\/IJCNN.2011.6033395"},{"key":"10.1016\/j.ress.2026.113281_b52","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, et al. Deep residual learning for image recognition. In: Proc. IEEE conf. comput. vis. pattern recognit.. CVPR, 2016, p. 770\u20138.","DOI":"10.1109\/CVPR.2016.90"},{"issue":"2","key":"10.1016\/j.ress.2026.113281_b53","first-page":"2492","article-title":"DisBezant: Secure and robust federated learning against Byzantine attack in IoT-enabled MTS","volume":"24","author":"Ma","year":"2023","journal-title":"IEEE Trans Intell Transp Syst"}],"container-title":["Reliability Engineering &amp; System Safety"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0951832026010902?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0951832026010902?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T14:33:54Z","timestamp":1789223634000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0951832026010902"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":53,"alternative-id":["S0951832026010902"],"URL":"https:\/\/doi.org\/10.1016\/j.ress.2026.113281","relation":{},"ISSN":["0951-8320"],"issn-type":[{"value":"0951-8320","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Spectrum-feature-aware robust federated learning for malicious client detection","name":"articletitle","label":"Article Title"},{"value":"Reliability Engineering & System Safety","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ress.2026.113281","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":"113281"}}