relation: https://khub.utp.edu.my/scholars/18939/
title: Ensuring Trustworthy Machine Learning: Ethical Foundations, Robust Algorithms, and Responsible Applications
creator: Usmani, U.A.
creator: Usmani, A.Y.
creator: Usmani, M.U.
description: Intrusion detection, a pivotal facet of securing digital environments, intersects with the proliferation of machine learning (ML) technologies, which have driven transformative advancements across industries. This research paper systematically investigates the multifaceted challenges and solutions within this critical domain, weaving together ethical foundations, robust algorithms, responsible applications, and intrusion detection. Commencing with a comprehensive exploration of intrusion detection's paramount importance in safeguarding digital realms, we delve into the ethical underpinnings of ML, meticulously analyzing facets such as transparency, fairness, and bias mitigation within the context of intrusion detection. Significantly, this study places a strong emphasis on the methodology adopted for intrusion detection, highlighting its robustness and effectiveness in addressing these ethical challenges. With a specific focus on algorithmic robustness, we explore a plethora of techniques that enhance the resilience of ML models against adversarial attacks, uncertainties, and potential intrusions within the proposed framework. Furthermore, this paper meticulously examines the responsible application of ML, particularly in sensitive domains, elucidating strategies aimed at aligning technology with societal values and enhancing security. This holistic exploration culminates in the presentation of a comprehensive framework that serves as an indispensable guiding resource for researchers, practitioners, and policymakers deeply committed to harnessing the immense potential of machine learning addressing ethical aspects (22 focus), algorithmic robustness (35 focus), and responsible application (23 ), offering comprehensive guidance. © 2023 IEEE.
publisher: Institute of Electrical and Electronics Engineers Inc.
date: 2023
type: Conference or Workshop Item
type: PeerReviewed
identifier:   Usmani, U.A. and Usmani, A.Y. and Usmani, M.U.  (2023) Ensuring Trustworthy Machine Learning: Ethical Foundations, Robust Algorithms, and Responsible Applications.  In: UNSPECIFIED.     
relation: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85186494089&doi=10.1109%2fICCCIS60361.2023.10425285&partnerID=40&md5=666f016f193da7dfbba461f52d7f318e
relation: 10.1109/ICCCIS60361.2023.10425285
identifier: 10.1109/ICCCIS60361.2023.10425285