{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T11:27:38Z","timestamp":1762342058177,"version":"3.37.3"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2023,3,31]],"date-time":"2023-03-31T00:00:00Z","timestamp":1680220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,3,31]],"date-time":"2023-03-31T00:00:00Z","timestamp":1680220800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100008530","name":"FEDER","doi-asserted-by":"crossref","award":["NUP: POCI-01-0247-FEDER- 045220"],"award-info":[{"award-number":["NUP: POCI-01-0247-FEDER- 045220"]}],"id":[{"id":"10.13039\/501100008530","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Computing"],"published-print":{"date-parts":[[2023,9]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Edge computing and multi-access edge computing (MEC) are two recent paradigms of distributed computing that are growing due to the rise of the fifth-generation (5G) of broadband cellular networks. The development of edge computing and MEC architectures involves the hosting of applications close to the end-users, allowing: an improved privacy, given that critical data is not shared with other systems; a reduced communication latency; an improved application speed; and a more efficient energy use. However, many applications are challenged by edge computing and MEC. In the case of machine learning (ML) applications, there can be privacy rules that do not allow data to be shared among distinct edges. Additionally, the devices used to train ML models might present lower computational capabilities than traditional computers. In this work, we present a Federated ML architecture that uses decentralized data and light ML training techniques to fit ML models on the 5G Edge. Our system consists of edge nodes that train models using local data and a centralized node that aggregates the results. As a case study, an international revenue share fraud task is addressed by considering two real-world datasets obtained from a commercial provider of Telecom analytics solutions. We test our architecture using two iterations of a Federated ML method, then compare it with a centralized ML model that is currently adopted by the provider. The results show that the Federated Learning decentralized approach produces an excellent level of class discrimination and that the main models maintain the performance across two rounds of decentralized training and even surpass the existing centralized model. After validating the results with the Telecom provider, we have built a prototype technological architecture that can be deployed in a real-world MEC scenario.<\/jats:p>","DOI":"10.1007\/s00607-023-01174-w","type":"journal-article","created":{"date-parts":[[2023,4,4]],"date-time":"2023-04-04T11:52:19Z","timestamp":1680609139000},"page":"1907-1932","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["International revenue share fraud prediction on the 5G edge using federated learning"],"prefix":"10.1007","volume":"105","author":[{"given":"Lu\u00eds","family":"Ferreira","sequence":"first","affiliation":[]},{"given":"Leopoldo","family":"Silva","sequence":"additional","affiliation":[]},{"given":"Francisco","family":"Morais","sequence":"additional","affiliation":[]},{"given":"Carlos Manuel","family":"Martins","sequence":"additional","affiliation":[]},{"given":"Pedro Miguel","family":"Pires","sequence":"additional","affiliation":[]},{"given":"Helena","family":"Rodrigues","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7991-2090","authenticated-orcid":false,"given":"Paulo","family":"Cortez","sequence":"additional","affiliation":[]},{"given":"Andr\u00e9","family":"Pilastri","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,3,31]]},"reference":[{"key":"1174_CR1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2938534","author":"N Hassan","year":"2019","unstructured":"Hassan N, Yau K-L, Celimuge W (2019) Edge computing in 5G: a review. IEEE Access. https:\/\/doi.org\/10.1109\/ACCESS.2019.2938534","journal-title":"IEEE Access"},{"issue":"2","key":"1174_CR2","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1016\/j.dcan.2017.07.001","volume":"4","author":"Y Ai","year":"2018","unstructured":"Ai Y, Peng M, Zhang K (2018) Edge computing technologies for internet of things: a primer. Digit Commun Netw 4(2):77\u201386. https:\/\/doi.org\/10.1016\/j.dcan.2017.07.001","journal-title":"Digit Commun Netw"},{"key":"1174_CR3","unstructured":"(2019) ETSI. Multi-access edge computing (MEC) framework and reference architecture. ETSI GS MEC, 3"},{"key":"1174_CR4","unstructured":"(2012) Black Swan\u00a0Telecom Journal. International revenue share fraud: are we winning the battle against telecom pirates? http:\/\/bswan.org\/revenue_share_fraud.asp"},{"key":"1174_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/S1361-3723(13)70027-7","author":"M Yelland","year":"2013","unstructured":"Yelland M (2013) Fraud in mobile networks. Comput Fraud Secur. https:\/\/doi.org\/10.1016\/S1361-3723(13)70027-7","journal-title":"Comput Fraud Secur"},{"key":"1174_CR6","unstructured":"(2016) European Union. General Data Protection Regulation (GDPR). https:\/\/gdpr.eu\/tag\/gdpr\/"},{"key":"1174_CR7","doi-asserted-by":"publisher","unstructured":"Ferreira L, Silva L, Pinho D, Morais F, Martins CM, Pires PM, Fidalgo P, Rodrigues H, Cortez P, Pilastri A (2022) A federated machine learning approach to detect international revenue share fraud on the 5g edge. In: 37th symposium on applied computing. ACM. https:\/\/doi.org\/10.1145\/3477314.3507322","DOI":"10.1145\/3477314.3507322"},{"key":"1174_CR8","unstructured":"(2017) IEEE. Ieee 5g and beyond technology roadmap [white paper]. https:\/\/futurenetworks.ieee.org\/images\/files\/pdf\/ieee-5g-roadmap-white-paper.pdf"},{"issue":"1","key":"1174_CR9","doi-asserted-by":"publisher","first-page":"450","DOI":"10.1109\/JIOT.2017.2750180","volume":"5","author":"N Abbas","year":"2018","unstructured":"Abbas N, Zhang Y, Taherkordi A, Skeie T (2018) Mobile edge computing: a survey. IEEE Internet Things J 5(1):450\u2013465. https:\/\/doi.org\/10.1109\/JIOT.2017.2750180","journal-title":"IEEE Internet Things J"},{"key":"1174_CR10","doi-asserted-by":"publisher","unstructured":"Sahin M, Francillon A, Gupta P, Ahamad M (2017) Sok: fraud in telephony networks. In: 2017 IEEE EuroS &P. https:\/\/doi.org\/10.1109\/EuroSP.2017.40","DOI":"10.1109\/EuroSP.2017.40"},{"key":"1174_CR11","unstructured":"(2021) Communications Fraud\u00a0Control Association. Fraud loss survey report 2021. https:\/\/cfca.org\/wp-content\/uploads\/2021\/12\/CFCA-Fraud-Loss-Survey-2021-2.pdf"},{"key":"1174_CR12","unstructured":"Mobileum (2022) Revenue share fraud. www.mobileum.com\/products\/risk-management\/fraud-management\/revenue-share-fraud\/"},{"key":"1174_CR13","doi-asserted-by":"publisher","unstructured":"Meijaard Y, Cappers B, Mengerink J, Zannone N (2020) Predictive analytics to prevent voice over IP international revenue sharing fraud, pp 241\u2013260. https:\/\/doi.org\/10.1007\/978-3-030-49669-2_14","DOI":"10.1007\/978-3-030-49669-2_14"},{"key":"1174_CR14","doi-asserted-by":"publisher","unstructured":"Sahin M, Francillon A (2021) Understanding and detecting international revenue share fraud. In: 28th NDSS, virtually, February 21\u201325, 2021. https:\/\/doi.org\/10.14722\/ndss.2021.24051","DOI":"10.14722\/ndss.2021.24051"},{"key":"1174_CR15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2774837","author":"S Rathore","year":"2018","unstructured":"Rathore S, Sharma PK, Sangaiah AK, Park JJ (2018) A hesitant fuzzy based security approach for fog and mobile-edge computing. IEEE Access. https:\/\/doi.org\/10.1109\/ACCESS.2017.2774837","journal-title":"IEEE Access"},{"issue":"4","key":"1174_CR16","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1109\/MCOM.2018.1700817","volume":"56","author":"A Ghoneim","year":"2018","unstructured":"Ghoneim A, Muhammad G, Amin SU, Gupta BB (2018) Medical image forgery detection for smart healthcare. IEEE Commun Mag 56(4):33\u201337. https:\/\/doi.org\/10.1109\/MCOM.2018.1700817","journal-title":"IEEE Commun Mag"},{"key":"1174_CR17","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3099597","author":"H Xiao","year":"2021","unstructured":"Xiao H, Zhao J, Pei Q, Feng J, Liu L, Shi W (2021) Vehicle selection and resource optimization for federated learning in vehicular edge computing. IEEE Trans Intell Transp Syst. https:\/\/doi.org\/10.1109\/TITS.2021.3099597","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"1174_CR18","doi-asserted-by":"publisher","first-page":"69194","DOI":"10.1109\/ACCESS.2019.2919736","volume":"7","author":"J Ren","year":"2019","unstructured":"Ren J, Wang H, Hou T, Zheng S, Tang C (2019) Federated learning-based computation offloading optimization in edge computing-supported internet of things. IEEE Access 7:69194\u201369201. https:\/\/doi.org\/10.1109\/ACCESS.2019.2919736","journal-title":"IEEE Access"},{"issue":"5","key":"1174_CR19","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1109\/MNET.2019.1800286","volume":"33","author":"W Xiaofei","year":"2019","unstructured":"Xiaofei W, Yiwen H, Chenyang W, Qiyang Zhao X, Chen CM (2019) In-edge AI: intelligentizing mobile edge computing, caching and communication by federated learning. IEEE Netw 33(5):156\u2013165. https:\/\/doi.org\/10.1109\/MNET.2019.1800286","journal-title":"IEEE Netw"},{"issue":"4","key":"1174_CR20","doi-asserted-by":"publisher","first-page":"2238","DOI":"10.1109\/JIOT.2020.3026589","volume":"8","author":"Yu Shuai","year":"2021","unstructured":"Shuai Yu, Chen X, Zhou Z, Gong X, Di W (2021) When deep reinforcement learning meets federated learning: intelligent multitimescale resource management for multiaccess edge computing in 5g ultradense network. IEEE Internet Things J 8(4):2238\u20132251. https:\/\/doi.org\/10.1109\/JIOT.2020.3026589","journal-title":"IEEE Internet Things J"},{"issue":"3","key":"1174_CR21","doi-asserted-by":"publisher","first-page":"2134","DOI":"10.1109\/TII.2019.2942179","volume":"16","author":"L Yunlong","year":"2020","unstructured":"Yunlong L, Huang X, Dai Y, Maharjan S, Zhang Y (2020) Differentially private asynchronous federated learning for mobile edge computing in urban informatics. IEEE Trans Ind Inform 16(3):2134\u20132143. https:\/\/doi.org\/10.1109\/TII.2019.2942179","journal-title":"IEEE Trans Ind Inform"},{"key":"1174_CR22","doi-asserted-by":"publisher","first-page":"562","DOI":"10.1016\/j.ins.2019.07.069","volume":"505","author":"Y Qian","year":"2019","unstructured":"Qian Y, Long H, Chen J, Guan X, Hassan MM, Alelaiwi A (2019) Privacy-aware service placement for mobile edge computing via federated learning. Inf Sci 505:562\u2013570. https:\/\/doi.org\/10.1016\/j.ins.2019.07.069","journal-title":"Inf Sci"},{"key":"1174_CR23","doi-asserted-by":"publisher","first-page":"209191","DOI":"10.1109\/ACCESS.2020.3038287","volume":"8","author":"Y Ye","year":"2020","unstructured":"Ye Y, Li S, Liu F, Tang Y, Wanting H (2020) Edgefed: optimized federated learning based on edge computing. IEEE Access 8:209191\u2013209198. https:\/\/doi.org\/10.1109\/ACCESS.2020.3038287","journal-title":"IEEE Access"},{"key":"1174_CR24","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3056919","author":"W Zhang","year":"2021","unstructured":"Zhang W, Wang X, Zhou P, Weiwei W, Zhang X (2021) Client selection for federated learning with non-iid data in mobile edge computing. IEEE Access. https:\/\/doi.org\/10.1109\/ACCESS.2021.3056919","journal-title":"IEEE Access"},{"issue":"5","key":"1174_CR25","doi-asserted-by":"publisher","first-page":"3310","DOI":"10.1109\/JIOT.2020.3023126","volume":"8","author":"J Zhang","year":"2021","unstructured":"Zhang J, Chen B, Cheng X, Binh HTT, Shui Yu (2021) Poisongan: generative poisoning attacks against federated learning in edge computing systems. IEEE Internet Things J 8(5):3310\u20133322. https:\/\/doi.org\/10.1109\/JIOT.2020.3023126","journal-title":"IEEE Internet Things J"},{"key":"1174_CR26","doi-asserted-by":"publisher","unstructured":"Yu Z, Hu J, Min G, Lu H, Zhao Z, Wang H, Georgalas N (2018) Federated learning based proactive content caching in edge computing. In: IEEE GLOBECOM 2018, Abu Dhabi, 2018. IEEE, pp 1\u20136. https:\/\/doi.org\/10.1109\/GLOCOM.2018.8647616","DOI":"10.1109\/GLOCOM.2018.8647616"},{"issue":"6","key":"1174_CR27","doi-asserted-by":"publisher","first-page":"1205","DOI":"10.1109\/JSAC.2019.2904348","volume":"37","author":"S Wang","year":"2019","unstructured":"Wang S, Tuor T, Salonidis T, Leung KK, Makaya C, He T, Chan K (2019) Adaptive federated learning in resource constrained edge computing systems. IEEE J Sel Areas Commun 37(6):1205\u20131221. https:\/\/doi.org\/10.1109\/JSAC.2019.2904348","journal-title":"IEEE J Sel Areas Commun"},{"key":"1174_CR28","doi-asserted-by":"publisher","first-page":"23920","DOI":"10.1109\/ACCESS.2020.2968399","volume":"8","author":"D Ye","year":"2020","unstructured":"Ye D, Rong Yu, Pan M, Han Z (2020) Federated learning in vehicular edge computing: a selective model aggregation approach. IEEE Access 8:23920\u201323935. https:\/\/doi.org\/10.1109\/ACCESS.2020.2968399","journal-title":"IEEE Access"},{"issue":"1","key":"1174_CR29","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1049\/trit.2019.0049","volume":"5","author":"R Fantacci","year":"2020","unstructured":"Fantacci R, Picano B (2020) Federated learning framework for mobile edge computing networks. CAAI Trans Intell Technol 5(1):15\u201321. https:\/\/doi.org\/10.1049\/trit.2019.0049","journal-title":"CAAI Trans Intell Technol"},{"key":"1174_CR30","doi-asserted-by":"publisher","unstructured":"Ta\u00efk A, Cherkaoui S (2020) Electrical load forecasting using edge computing and federated learning. In: IEEE ICC, 2020. IEEE, pp 1\u20136. https:\/\/doi.org\/10.1109\/ICC40277.2020.9148937","DOI":"10.1109\/ICC40277.2020.9148937"},{"key":"1174_CR31","doi-asserted-by":"publisher","unstructured":"Chen D, Xie J, Kim B, Wang L, Hong CS, Wang L-C, Han Z (2020) Federated learning based mobile edge computing for augmented reality applications. In: ICNC 2020, USA, 2020. IEEE, pp 767\u2013773. https:\/\/doi.org\/10.1109\/ICNC47757.2020.9049708","DOI":"10.1109\/ICNC47757.2020.9049708"},{"issue":"11","key":"1174_CR32","doi-asserted-by":"publisher","first-page":"11053","DOI":"10.1109\/JIOT.2020.2994596","volume":"7","author":"H Sun","year":"2020","unstructured":"Sun H, Shiqi Li F, Richard Yu, Qi Q, Wang J, Liao J (2020) Toward communication-efficient federated learning in the internet of things with edge computing. IEEE Internet Things J 7(11):11053\u201311067. https:\/\/doi.org\/10.1109\/JIOT.2020.2994596","journal-title":"IEEE Internet Things J"},{"issue":"6","key":"1174_CR33","doi-asserted-by":"publisher","first-page":"2421","DOI":"10.1007\/s11036-020-01586-4","volume":"25","author":"J Zhang","year":"2020","unstructured":"Zhang J, Zhao Y, Wang J, Chen B (2020) Fedmec: improving efficiency of differentially private federated learning via mobile edge computing. Mob Netw Appl 25(6):2421\u20132433. https:\/\/doi.org\/10.1007\/s11036-020-01586-4","journal-title":"Mob Netw Appl"},{"issue":"7","key":"1174_CR34","doi-asserted-by":"publisher","first-page":"1539","DOI":"10.1109\/TPDS.2020.3040867","volume":"32","author":"W Wentai","year":"2021","unstructured":"Wentai W, He L, Lin W, Mao R (2021) Accelerating federated learning over reliability-agnostic clients in mobile edge computing systems. IEEE Trans Parallel Distrib Syst 32(7):1539\u20131551. https:\/\/doi.org\/10.1109\/TPDS.2020.3040867","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"1174_CR35","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.011.2000295","author":"R Yu","year":"2021","unstructured":"Yu R, Li P (2021) Toward resource-efficient federated learning in mobile edge computing. IEEE Netw. https:\/\/doi.org\/10.1109\/MNET.011.2000295","journal-title":"IEEE Netw"},{"key":"1174_CR36","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2021.3087125","author":"C Feng","year":"2021","unstructured":"Feng C, Zhao Z, Wang Y, Quek T, Peng M (2021) On the design of federated learning in the mobile edge computing systems. Trans Commun. https:\/\/doi.org\/10.1109\/TCOMM.2021.3087125","journal-title":"Trans Commun"},{"key":"1174_CR37","unstructured":"McMahan B, Moore E, Ramage D, Hampson S, y Arcas BA (2017) Communication-efficient learning of deep networks from decentralized data. In: Proceedings of the 20th international conference on AI and statistics, vol 54. PMLR, pp 1273\u20131282"},{"key":"1174_CR38","unstructured":"(2022) TensorFlow. TensorFlow. https:\/\/www.tensorflow.org\/"},{"issue":"8","key":"1174_CR39","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1016\/j.patrec.2005.10.010","volume":"27","author":"T Fawcett","year":"2006","unstructured":"Fawcett T (2006) An introduction to ROC analysis. Pattern Recognit Lett 27(8):861\u2013874. https:\/\/doi.org\/10.1016\/j.patrec.2005.10.010","journal-title":"Pattern Recognit Lett"},{"key":"1174_CR40","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.114287","author":"P Pereira","year":"2021","unstructured":"Pereira P, Cortez P, Mendes R (2021) Multi-objective grammatical evolution of decision trees for mobile marketing user conversion prediction. Expert Syst Appl. https:\/\/doi.org\/10.1016\/j.eswa.2020.114287","journal-title":"Expert Syst Appl"},{"issue":"3","key":"1174_CR41","doi-asserted-by":"publisher","first-page":"515","DOI":"10.1016\/j.eswa.2005.09.080","volume":"31","author":"S-Y Hung","year":"2006","unstructured":"Hung S-Y, Yen DC, Wang H-Y (2006) Applying data mining to telecom churn management. Expert Syst Appl 31(3):515\u2013524. https:\/\/doi.org\/10.1016\/j.eswa.2005.09.080","journal-title":"Expert Syst Appl"},{"key":"1174_CR42","volume-title":"Microservices patterns","author":"C Richardson","year":"2019","unstructured":"Richardson C (2019) Microservices patterns. Manning"}],"container-title":["Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00607-023-01174-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00607-023-01174-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00607-023-01174-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T14:05:31Z","timestamp":1693231531000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00607-023-01174-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,31]]},"references-count":42,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2023,9]]}},"alternative-id":["1174"],"URL":"https:\/\/doi.org\/10.1007\/s00607-023-01174-w","relation":{},"ISSN":["0010-485X","1436-5057"],"issn-type":[{"type":"print","value":"0010-485X"},{"type":"electronic","value":"1436-5057"}],"subject":[],"published":{"date-parts":[[2023,3,31]]},"assertion":[{"value":"26 May 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 March 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 March 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}