Federated Learning for Privacy-Preserving Conversational AI in Retail Clouds

  • Authors

    • Dr. Grace Ndlovu Associate Professor, University of Pretoria, South Africa. Author
    • Mr. Samuel Johnson Senior Operations Manage, MTN Group, South Africa. Author

    DOI:

    https://doi.org/10.67228/30713315/IJAIDT-2020PI2F8Y

    Published 04-04-2020

  • Federated Learning, Privacy-Preserving AI, Conversational AI, Retail Cloud Computing, Differential Privacy, Secure Aggregation, Customer Service Automation, Natural Language Processing (NLP), Data Privacy In AI, Edge Computing In Retail

    Issue

    Vol. 3 No. 1 (2020)

    Section

    Articles

    How to Cite

    [1]
    G. Ndlovu and S. Johnson, “Federated Learning for Privacy-Preserving Conversational AI in Retail Clouds”, IJAIDT, vol. 3, no. 1, pp. 01–11, Apr. 2020, doi: 10.67228/30713315/IJAIDT-2020PI2F8Y.

  • Abstract

    This document provides detailed guidelines for the preparation and submission of manuscripts to World Comet Research Group Journals. The abstract should present a concise and self-contained summary of the research, clearly stating the purpose, methodology, key findings, and principal conclusions of the study. Authors are required to limit the abstract to a maximum of 300 words. Emphasis should be placed on the novelty and significance of the research contribution, clearly distinguishing the work from existing studies in the field. The abstract should be written in clear and precise academic language and must avoid the use of references, figures, tables, or unexplained abbreviations. As the abstract is often the first and sometimes the only part of the paper read by reviewers and readers, it should accurately reflect the content of the manuscript and highlight the original aspects and potential impact of the work. Compliance with these guidelines will facilitate effective peer review, indexing, and dissemination of articles published in World Comet Research Group Journals.

  • References

    [1] McMahan, H. B., et al. "Communication-efficient learning of deep networks from decentralized data." Artificial Intelligence and Statistics. 2017.

    [2] Geyer, R. C., Klein, T., & Nabi, M. "Differentially private federated learning: A client-level perspective." NeurIPS Workshop on Machine Learning on the Phone and other Consumer Devices, 2017.

    [3] Bonawitz, K., et al. "Practical secure aggregation for privacy-preserving machine learning." Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security, 2017.

    [4] Shokri, R., & Shmatikov, V. "Privacy-preserving deep learning." Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security, 2015.

    [5] Nasr, M., Shokri, R., & Houmansadr, A. "Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning." IEEE S&P, 2019.

    [6] Li, T., et al. "Federated optimization in heterogeneous networks." Proceedings of Machine Learning and Systems, 2020.

    [7] Hard, A., et al. "Federated learning for mobile keyboard prediction." arXiv preprint arXiv:1811.03604, 2018.

    [8] Rieke, N., et al. "The future of digital health with federated learning." npj Digital Medicine, 2020.

    [9] Yang, Q., et al. "Federated machine learning: Concept and applications." ACM Transactions on Intelligent Systems and Technology, 2019.

    [10] Truong, N. B., et al. "Privacy preservation in federated learning: A blockchain-based framework." IEEE Internet of Things Journal, 2020.

    [11] Abadi, M., et al. "Deep learning with differential privacy." Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security, 2016.

    [12] Bhowmick, A., et al. "Protection against membership inference attacks in federated learning using adversarial regularization." arXiv preprint arXiv:1812.00910, 2018.

    [13] Melis, L., et al. "Exploiting unintended feature leakage in collaborative learning." IEEE S&P, 2019.

  • Downloads