IJDSBDA International Journal of Data Science and Big Data Analytics 2710-2599 SvedbergOpen ijdsbda-1-2-001 10.51483/IJDSBDA.1.2.2021.1-13 Research Paper Federated learning for privacy-preserving data access SmietankaMalgorzata 1 * PithadiaHirsh 2 TreleavenPhilip 3 1University College London, Gower St, Bloomsbury, London WC1E 6BT, United Kingdom. E-mail: malgorzata.wasiewicz.17@ucl.ac.uk 2University College London, Gower St, Bloomsbury, London WC1E 6BT, United Kingdom. E-mail: H.Pithadia@cs.ucl.ac.uk 3University College London, Gower St, Bloomsbury, London WC1E 6BT, United Kingdom. E-mail: p.treleaven@ucl.ac.uk *Corresponding author: Malgorzata Smietanka, University College London, Gower St, Bloomsbury, London WC1E 6BT, United Kingdom. E-mail: malgorzata.wasiewicz.17@ucl.ac.uk 05 2021 1 2 1 13 Abstract

Federated learning is a pioneering privacy-preserving data technology and also a new machine learning model trained on distributed data sets. Companies collect huge amounts of historic and real-time data to drive their business and collaborate with other organizations. However, data privacy is becoming increasingly important because of regulations (e.g., EU GDPR) and the need to protect their sensitive and personal data. Companies need to manage data access: firstly within their organizations (so they can control staff access), and secondly protecting raw data when collaborating with third parties. What is more, companies are increasingly looking to ‘monetize’ the data they’ve collected. However, under new legislations, utilizing data by different organization is becoming increasingly difficult (Yu, 2016). Federated learning pioneered by Google is the emerging privacy- preserving data technology and also a new class of distributed machine learning models. This paper discusses federated learning as a solution for privacy-preserving data access and distributed machine learning applied to distributed data sets. It also presents a privacy-preserving federated learning infrastructure.

 Keywords Federated Learning Privacy Machine Learning Data Science InsurTech References BarrenoM. et al. (2006). Can machine learning be secure?. Proceedings of the 2006 ACM Symposium on Information, computer and communications security - ASIACCS ‘06. BrisimiT.S. et al. (2018). Federated learning of predictive models from federated electronic health records. International Journal of Medical Informatics. 112, 59–67. ChoudhuryO. et al. (2019). Predicting adverse drug reactions on distributed health data using federated learning. AMIA Annu Symp Proc., 313–322. CohanP. (2018). Forbes. [Online] Available at: https://www.forbes.com/sites/petercohan/2018/07/22/mastercard-amex-and-envestnet-profit-from-400m-business-of-selling-transaction-data/#5e576d4f7722 [Accessed 22 07 2018]. CramerR.DamgårdI.NielsenJ. (2000). Multiparty computation from threshold homomorphic encryption. Lecture Notes in Computer Science, 11(7). DamgårdI.PastroV.SmartN.ZakariasS. (2012). Multiparty computation from somewhat homomorphic encryption.s.l., s.n., 643–662. Data Model, 2. (2020). Wikipedia. [Online] Available at: https://en.wikipedia.org/wiki/Data_model#:~:text=A%20data%20model%20(or%20datamodel,properties%20of%20real%2Dworld%20entities. [Accessed 28 08 2020]. DerwischS. (2019). Data Monetization - Use Cases, Implementation and Added Value, s.l.: BARC. Facebook_data_scandal (2020). Wikipedia. [Online] Available at: https://en.wikipedia.org/wiki/Facebook-Cambridge_Analytica_data_scandal [Accessed 05 08 2020]. GDPR (2018). GDPR. [Online] Available at: https://gdpr-info.eu/ [Accessed 05 08 2020]. Gilad-BachrachR. et al. (2016). Cryptonets: Applying neural networks to encrypted data with high throughput and accuracy. s.l., s.n., 201–210. GoogleAI (2017). Google AI Blog. [Online] Available at: https://ai.googleblog.com/2017/04/federated-learning-collaborative.html. [Accessed 05 08 2020] HardyC.Le MerrerE.SericolaB. (2018). Gossiping GANs. Proceedings of the Second Workshop on Distributed Infrastructures for Deep Learning - DIDL’18. HuangL.LiuD. (2019). Patient clustering improves efficiency of federated machine learning to predict mortality and hospital stay time using distributed electronic medical records.. arXiv:1903.09296. KellerM.OrsiniE.SchollP. (2016). MASCOT. Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security. KonečnýJ.McMahanB. H.RamageD.RichtárikP. (2016). Federated Optimization: Distributed Machine Learning for On-Device Intelligence. https://arxiv.org/abs/1610.02527. KonečnýJ. et al. (2017). Federated Learning: Strategies for Improving Communication Efficiency. https://arxiv.org/abs/1610.05492. KotyA. C. (2019). China Briefing. [Online] Available at: https://www.china-briefing.com/news/chinas-corporate-social-credit-system-how-it-works/ [Accessed 03 08 2020]. LeeJ. et al. (2018). Privacy-preserving patient similarity learning in a federated environment: development and analysis.. JMIR Medical Informatics, 6(2). LiW. et al. (2019). Privacy-preserving federated brain tumour segmentation. In: Machine Learning in Medical Imaging. MLMI2019. Lecture Notes in Computer Science. s.l.:Springer, Cham, pp. 133–141. McMahanB.H. et al. (2017). Communication-Efficient Learning of Deep Networks from Decentralized Data. https://arxiv.org/abs/1602.05629. MELLODDY (2020). MELLODDY project. [Online] Available at: https://www.melloddy.eu/ [Accessed 10 09 2020]. OpenMined (2020). OpenMined Blog. [Online] Available at: https://blog.openmined.org/federated-credit-scoring/ [Accessed 03 08 2020]. PapernotN. et al. (2020). Scalable Private Learning with PATE.s.l.:s.n. PyGridO. (2020). PyGrid OpenMined. [Online] Available at: https://github.com/OpenMined/PyGrid [Accessed 08 2020]. RivestR.L.AdlemanL.DertouzosM.L. and others (1978). On data banks and privacy homomorphisms. Foundations of Secure Computation. 4, 169–180. ShamirA. (1979). How to share a secret. Communications of the ACM. 22, 612–613. ŚmietankaM.KoshiyamaA.TreleavenP. (2020). Algorithms in Future Insurance Markets. https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3641518. SurdenH., (2019). Artificial intelligence and law: An overview. Georgia State University Law Review, 35, 19–22. TreleavenP.Gendal BrownR.YangD. (2017). Blockchain technology in finance. Computer, 50(9), 14–17. TureaM. (2019). Healthcare innovation. [Online] Available at: https://healthcareweekly.com/how-the-big-4-tech-companies-are-leading-healthcare-innovation/ [Accessed 11 08 2020]. Wikipedia (2020a). Data exchange. [Online] Available at: https://en.wikipedia.org/wiki/Data_exchange [Accessed 05 08 2020]. Wikipedia (2020b). Data model. [Online] Available at: https://en.wikipedia.org/wiki/Data_model [Accessed 05 08 2020]. Wikipedia (2020c). Digital object identifier. [Online] Available at: https://en.wikipedia.org/wiki/Digital_object_identifier [Accessed 05 08 2020]. Wikipedia (2020d). Markup language. [Online] Available at: https://en.wikipedia.org/wiki/Markup_language [Accessed 05 08 2020]. YangQ. et al. (2019a). Federated learning. Synthesis Lectures on Artificial Intelligence and Machine Learning, 13, 1–207. YangQ. et al. (2019b). Federated Learning. Synthesis Lectures on Artificial Intelligence and Machine Learning.s.l. :Morgan & Claypool Publishers. YangQ.LiuY.ChenT. (2019c). Federated machine learning: Concept and applications. http://arxiv.org/abs/1902.04885. YangW. et al. (2019d). FFD: A federated learning based method for credit card fraud detection. Notes in Computer Science, Springer. 11514, 18–32. YaoA. C.C. (1986). How to generate and exchange secrets - IEEE Conference Publication. s.l.:s.n. YuS. (2016). Big privacy: Challenges and opportunities of privacy study in the age of big data. IEEEAccess, 4(2016), 2751–2763. ZhaoY. et al. (2019). Mobile edge computing, blockchain and reputation-based crowdsourcing iot federated learning: A secure, decentralized and privacy-preserving system.. arXiv:1906.10893. ZouY. et al. (2019). Mobile Device Training Strategies in Federated Learning: An Evolutionary Game Approach. International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData) ,874–879.