Fortifying Machine Learning, Data Privacy, and Secure Collaboration
- 31 May 2024
- book chapter
- Published by IGI Global Scientific Publishing
- p. 172-191
Abstract
The utilitarianism of machine learning (ML) techniques introduces an additional layer of security to ML applications. In the domain of cybersecurity, ML continuously evolves by analyzing data to identify patterns, thus enhancing the capacity to detect malware in encrypted traffic, recognize insider threats, predict online “bad neighborhoods” for safer browsing, and protect cloud-stored data by uncovering suspicious user behavior. Simultaneously, privacy-preserving techniques, exemplified by homomorphic encryption and multi-party computation, empower the training of ML models on sensitive data without exposing the raw information. Privacy-preserving techniques, notably statistical disclosure control (SDC), benefit data sharing. SDC seeks to mitigate the risk of disclosing confidential information by employing privacy-preserving techniques for data de-identification. Research integrates privacy-preserving techniques into ML, advancing diverse PPML for secure data analysis in academia and industry.Keywords
This publication has 8 references indexed in Scilit:
- Machine Learning and Blockchain: A Bibliometric Study on Security and PrivacyInformation, 2024
- Preserving data privacy in machine learning systemsComputers & Security, 2023
- A Review of Privacy Enhancement Methods for Federated Learning in Healthcare SystemsInternational Journal of Environmental Research and Public Health, 2023
- A supervised machine learning algorithm for detecting and predicting fraud in credit card transactionsDecision Analytics Journal, 2023
- From distributed machine learning to federated learning: a surveyKnowledge and Information Systems, 2022
- Digital technologies: tensions in privacy and dataJournal of the Academy of Marketing Science, 2022
- Detection of malicious software by analyzing the behavioral artifacts using machine learning algorithmsInformation and Software Technology, 2020
- Membership Inference Attacks Against Machine Learning Models2017