{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T01:36:30Z","timestamp":1760060190999,"version":"build-2065373602"},"reference-count":39,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T00:00:00Z","timestamp":1754265600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"TU Wien Open Access Funding Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computers"],"abstract":"<jats:p>Deep Federated Learning (DFL) revolutionizes machine learning (ML) by enabling collaborative model training across diverse, decentralized data sources without direct data sharing, emphasizing user privacy and data sovereignty. Despite its potential, DFL\u2019s application in sensitive sectors is hindered by challenges in meeting rigorous standards like the GDPR, with traditional setups struggling to ensure compliance and maintain trust. Addressing these issues, our research introduces an innovative Zero Trust-based DFL architecture designed for GDPR compliant systems, integrating advanced security and privacy mechanisms to ensure safe and transparent cross-node data processing. Our base paper proposed the basic GDPR-Compliant DFL Architecture. Now we validate the previously proposed architecture by formally verifying it using High-Level Petri Nets (HLPNs). This Zero Trust-based framework facilitates secure, decentralized model training without direct data sharing. Furthermore, we have also implemented a case study using the MNIST and CIFAR-10 datasets to evaluate the existing approach with the proposed Zero Trust-based DFL methodology. Our experiments confirmed its effectiveness in enhancing trust, complying with GDPR, and promoting DFL adoption in privacy-sensitive areas, achieving secure, ethical Artificial Intelligence (AI) with transparent and efficient data processing.<\/jats:p>","DOI":"10.3390\/computers14080317","type":"journal-article","created":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T15:30:06Z","timestamp":1754321406000},"page":"317","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Ensuring Zero Trust in GDPR-Compliant Deep Federated Learning Architecture"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-0323-3218","authenticated-orcid":false,"given":"Zahra","family":"Abbas","sequence":"first","affiliation":[{"name":"Institute of Information Technology, Quaid-e-Azam University Islamabad, Islamabad 45320, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3631-9868","authenticated-orcid":false,"given":"Sunila Fatima","family":"Ahmad","sequence":"additional","affiliation":[{"name":"Institute of Information Technology, Quaid-e-Azam University Islamabad, Islamabad 45320, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5083-0019","authenticated-orcid":false,"given":"Adeel","family":"Anjum","sequence":"additional","affiliation":[{"name":"Institute of Information Technology, Quaid-e-Azam University Islamabad, Islamabad 45320, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0123-3554","authenticated-orcid":false,"given":"Madiha Haider","family":"Syed","sequence":"additional","affiliation":[{"name":"Institute of Information Technology, Quaid-e-Azam University Islamabad, Islamabad 45320, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8195-1630","authenticated-orcid":false,"given":"Saif Ur Rehman","family":"Malik","sequence":"additional","affiliation":[{"name":"School of Computer Science and Statistics, Trinity College Dublin, The University of Dublin, College Green, D02 PN40 Dublin, Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8972-0949","authenticated-orcid":false,"given":"Semeen","family":"Rehman","sequence":"additional","affiliation":[{"name":"Institute of Computer Technology, Technical University of Vienna (TU Wien), 1040 Vienna, Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,8,4]]},"reference":[{"key":"ref_1","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."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"41928","DOI":"10.1109\/ACCESS.2023.3269980","article-title":"A Survey on Securing Federated Learning: Analysis of Applications, Attacks, Challenges, and Trends","volume":"11","author":"Neto","year":"2023","journal-title":"IEEE Access"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Voigt, P., and Von Dem Bussche, A. (2017). The EU General Data Protection Regulation (GDPR), Springer.","DOI":"10.1007\/978-3-319-57959-7"},{"key":"ref_4","first-page":"1","article-title":"A Latent Class Modeling Approach for Differentially Private Synthetic Data for Contingency Tables","volume":"12","author":"Nixon","year":"2022","journal-title":"J. Priv. Confidential."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2200000083","article-title":"Advances and Open Problems in Federated Learning","volume":"14","author":"Kairouz","year":"2021","journal-title":"Found. Trends Mach. Learn."},{"key":"ref_6","unstructured":"McMahan, B., Moore, E., Ramage, D., Hampson, S., and y Arcas, B.A. (2017, January 20\u201322). Communication-Efficient Learning of Deep Networks from Decentralized Data. Proceedings of the Artificial Intelligence and Statistics, Ft. Lauderdale, FL, USA."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Hussain, S., Anwar, S.M., and Majid, M. (2017, January 11\u201315). Brain Tumor Segmentation Using Cascaded Deep Convolutional Neural Network. Proceedings of the 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Jeju, Republic of Korea.","DOI":"10.1109\/EMBC.2017.8037243"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Ahmad, S.F., Abbas, Z., Syed, M.H., Anjum, A., and Rehman, S. (2024). Dynamic Cohort Formation with Hierarchical Blockchain Using GDP for Enhanced FL. Computers, 13.","DOI":"10.3390\/computers13120317"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3501298","article-title":"Iterative Design and Prototyping of Computer Vision Mediated Remote Sighted Assistance","volume":"29","author":"Xie","year":"2022","journal-title":"ACM Trans. Comput. Hum. Interact."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3339474","article-title":"Federated Machine Learning: Concept and Applications","volume":"10","author":"Yang","year":"2019","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"10548","DOI":"10.1109\/ACCESS.2023.3344029","article-title":"Exploring Deep Federated Learning for the Internet of Things: A GDPR-Compliant Architecture","volume":"12","author":"Abbas","year":"2024","journal-title":"IEEE Access"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"54","DOI":"10.32996\/jcsts.2024.6.4.8","article-title":"Zero Trust Architecture: Enhancing Cybersecurity in Enterprise Networks","volume":"6","author":"Bashir","year":"2024","journal-title":"J. Comput. Sci. Technol. Stud."},{"key":"ref_13","first-page":"207","article-title":"Zero Trust Architecture","volume":"800","author":"Stafford","year":"2020","journal-title":"NIST Spec. Publ."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"84486","DOI":"10.1109\/ACCESS.2022.3197671","article-title":"Explainable AI for Healthcare 5.0: Opportunities and Challenges","volume":"10","author":"Saraswat","year":"2022","journal-title":"IEEE Access"},{"key":"ref_15","first-page":"37","article-title":"Autoencoders, Unsupervised Learning, and Deep Architectures","volume":"Volume 27","author":"Guyon","year":"2011","journal-title":"Proceedings of the ICML Workshop on Unsupervised and Transfer Learning"},{"key":"ref_16","unstructured":"Guo, P., Wang, P., Zhou, J., Jiang, S., and Patel, V.M. (2021, January 20\u201325). RW4. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Colorado Springs, CO, USA."},{"key":"ref_17","unstructured":"Liu, M., Ho, S., Wang, M., Gao, L., Jin, Y., and Zhang, H. (2021). Federated Learning Meets Natural Language Processing: A Survey. arXiv."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Nguyen, A., Do, T., Tran, M., Nguyen, B.X., Duong, C., Phan, T., Tjiputra, E., and Tran, Q.D. (2022, January 4\u20139). Deep Federated Learning for Autonomous Driving. Proceedings of the 2022 IEEE Intelligent Vehicles Symposium (IV), Aachen, Germany.","DOI":"10.1109\/IV51971.2022.9827020"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"7849","DOI":"10.1007\/s11227-023-05763-6","article-title":"Blockchain-Enabled Federated Learning for Prevention of Power Terminals Threats in IoT Environment Using Edge Zero-Trust Model","volume":"80","author":"Rizwan","year":"2024","journal-title":"J. Supercomput."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Kang, H., Liu, G., Wang, Q., Meng, L., and Liu, J. (2023). Theory and Application of Zero Trust Security: A Brief Survey. Entropy, 25.","DOI":"10.3390\/e25121595"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Hale, B., Van Bossuyt, D.L., Papakonstantinou, N., and O\u2019Halloran, B. (2021, January 17\u201319). A Zero-Trust Methodology for Security of Complex Systems with Machine Learning Components. Proceedings of the International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, Virtual.","DOI":"10.1115\/DETC2021-70442"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Vucovich, M., Quinn, D., Choi, K., Redino, C., Rahman, A., and Bowen, E. (2024, January 8\u201310). FedBayes: A Zero-Trust Federated Learning Aggregation to Defend Against Adversarial Attacks. Proceedings of the 2024 IEEE 14th Annual Computing and Communication Workshop and Conference (CCWC), Las Vegas, NV, USA.","DOI":"10.1109\/CCWC60891.2024.10427896"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Bandara, E., Liang, X., Shetty, S., Mukkamala, R., Rahman, A., and Keong, N.W. (2022, January 20\u201323). Skunk\u2014A Blockchain and Zero Trust Security Enabled Federated Learning Platform for 5G\/6G Network Slicing. Proceedings of the 2022 19th Annual IEEE International Conference on Sensing, Communication, and Networking (SECON), Stockholm, Sweden.","DOI":"10.1109\/SECON55815.2022.9918536"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"103540","DOI":"10.1016\/j.adhoc.2024.103540","article-title":"A Federated Learning-Based Zero Trust Intrusion Detection System for Internet of Things","volume":"162","author":"Javeed","year":"2024","journal-title":"Ad Hoc Netw."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1109\/MWC.001.2300405","article-title":"Federated Zero Trust Architecture using Artificial Intelligence","volume":"31","author":"Hussain","year":"2024","journal-title":"IEEE Wirel. Commun."},{"key":"ref_26","unstructured":"Jensen, K. (2013). Coloured Petri Nets: Basic Concepts, Analysis Methods and Practical Use, Springer."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1007\/s100090050021","article-title":"The Practitioner\u2019s Guide to Coloured Petri Nets","volume":"2","author":"Kristensen","year":"1998","journal-title":"Int. J. Softw. Tools Technol. Transf."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1016\/0166-3615(94)90031-0","article-title":"Putting High-Level Petri Nets to Work in Industry","volume":"25","year":"1994","journal-title":"Comput. Ind."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1109\/JSYST.2015.2493565","article-title":"Modeling and Analysis of the Thermal Properties Exhibited by Cyberphysical Data Centers","volume":"11","author":"Malik","year":"2015","journal-title":"IEEE Syst. J."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TCC.2013.3","article-title":"Modeling and Analysis of State-of-the-Art VM-Based Cloud Management Platforms","volume":"1","author":"Malik","year":"2013","journal-title":"IEEE Trans. Cloud Comput."},{"key":"ref_31","unstructured":"De Moura, L., and Bj\u00f8rner, N. (April, January 29). Z3: An Efficient SMT Solver. Proceedings of the International Conference on Tools and Algorithms for the Construction and Analysis of Systems, Budapest, Hungary."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based Learning Applied to Document Recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proc. IEEE"},{"key":"ref_33","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., and Haffner, P. (2024, March 03). Modified National Institute of Standards and Technology (MNIST) Dataset. Available online: https:\/\/yann.lecun.com\/exdb\/mnist\/."},{"key":"ref_34","unstructured":"Zhao, Y., Li, M., Lai, L., Suda, N., Civin, D., and Chandra, V. (2018). Federated Learning with Non-IID Data. arXiv."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"e20891","DOI":"10.2196\/20891","article-title":"Federated Learning on Clinical Benchmark Data: Performance Assessment","volume":"22","author":"Lee","year":"2020","journal-title":"J. Med. Internet Res."},{"key":"ref_36","unstructured":"Giuste, F.O., and Vizcarra, J.C. (2020). CIFAR-10 Image Classification Using Feature Ensembles. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Truex, S., Liu, L., Chow, K.H., Gursoy, M.E., and Wei, W. (2020, January 27). LDP-Fed: Federated Learning with Local Differential Privacy. Proceedings of the 3rd ACM International Workshop on Edge Systems, Analytics and Networking, San Jose, CA, USA.","DOI":"10.1145\/3378679.3394533"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1109\/MCI.2022.3180932","article-title":"When Federated Learning Meets Blockchain: A New Distributed Learning Paradigm","volume":"17","author":"Ma","year":"2022","journal-title":"IEEE Comput. Intell. Mag."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"111459","DOI":"10.1016\/j.comnet.2025.111459","article-title":"Asynchronous Federated Learning Based Zero Trust Architecture for the Next Generation Industrial Control Systems","volume":"269","author":"Lv","year":"2025","journal-title":"Comput. Netw."}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/8\/317\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:23:05Z","timestamp":1760034185000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/8\/317"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,4]]},"references-count":39,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,8]]}},"alternative-id":["computers14080317"],"URL":"https:\/\/doi.org\/10.3390\/computers14080317","relation":{},"ISSN":["2073-431X"],"issn-type":[{"type":"electronic","value":"2073-431X"}],"subject":[],"published":{"date-parts":[[2025,8,4]]}}}