Federate Machine Learning: A Secure Paradigm for Collaborative AI in Privacy-Sensitive Domains

Kartheek Kalluri

doi:10.5281/zenodo.14551746

Federate Machine Learning: A Secure Paradigm for Collaborative AI in Privacy-Sensitive Domains

Author(s)	Kartheek Kalluri
Country	United States
Abstract	Federated machine learning (FML) is a disruption-oriented paradigm of feature development in artificial intelligence (AI). This has posed the traditional query of data privacy, whether one really complies with both and, hence, working in the sensitive areas of health care, finance, and the IoT (Internet of Things). FML enables decentralized training of AI models instead of the traditional centralized AI framework: it allows the use of several local devices or even servers whereby raw data remains in a local site while collaborative learning can be harnessed. It ensures that data is always secured through state-of-the-art privacy-preserving techniques such as differential privacy, secure multiparty computation, and homomorphic encryption during training and aggregation. It, therefore, implies the application of distributed architectures, federated optimization algorithms like Federated Averaging (Fed Avg), along iterations for continuance improvement. Activity-specific refinements have proved the operational applicability of increasing diagnostic capability in health care, enhancing fraud detection in finance, and adopting privacy-sensitive functionality for smart devices in the IoT. How much FML cares for ethical AI development is demonstrated not only by the adherence to legally binding obligations such as the GDPR but also by HIPAA. Empirical results show that considerable improvement has been achieved in the areas of privacy protection and model performance and scalability without affecting data security or stakeholder trust. Research opportunities have been identified for communication overhead, bias mitigation, and adaptive scalability. In essence, FML erects a complete and strong, privacy-first framework for ethical, scalable, and collaborative development of AI in parallel to evolving innovation with society and in line with regulatory requirements on use.
Keywords	Federated Machine Learning (FML), Data Privacy and Security, Privacy-Preserving Techniques, Distributed AI Frameworks, Federated Averaging (Fed Avg), Ethical AI Compliance, Scalability and Complex Mitigation
Published In	Volume 13, Issue 4, October-December 2022
Published On	2022-10-05
Cite This	Federate Machine Learning: A Secure Paradigm for Collaborative AI in Privacy-Sensitive Domains - Kartheek Kalluri - IJSAT Volume 13, Issue 4, October-December 2022. DOI 10.5281/zenodo.14551746
DOI	https://doi.org/10.5281/zenodo.14551746
Short DOI	https://doi.org/g8wtfg

View / Download PDF File

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJSAT DOI prefix is
10.71097/IJSAT

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 15 Isu 4 Cover Page Vol 15 Isu 3 Cover Page Vol 15 Isu 2

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJSAT Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us	Message on WhatsApp	+91-9687-182-185	editor@ijsat.org

International Journal on Science and Technology

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Federate Machine Learning: A Secure Paradigm for Collaborative AI in Privacy-Sensitive Domains

Share this