Home / Current Issue / Paper 1720158
Cybersecurity and Privacy Protection in AI-Driven Digital Environments
Subject area: Science,Engineering and Technology · Area of research: Artificial Intelligence
DOI: https://doi.org/10.64388/IREV10I1-1720158
Abstract
The rise of artificial intelligence (AI) has revolutionized the nature of cybersecurity, both in terms of its attack and defense capabilities, and also due to the new privacy threats that it poses. This paper reviews the literature systematically, and investigates the usage of AI technologies in the context of enhancing cyber-defence and safeguarding data privacy in AI-driven digital environments as well as their adverse usage and destabilisation by adversarial actors such as machine learning (ML), deep learning (DL), federated learning, and explainable AI (XAI). A total of 21 peer-reviewed and indexed sources have been analysed and thematically categorised into four areas: AI-based threat and intrusion detection, adversarial machine learning and model robustness, privacy-preserving AI techniques, and governance/regulatory compliance. The review reveals that, compared to signature-based approaches, AI can significantly improve accuracy of anomaly and intrusion detection, that federated learning and differential privacy provide mathematically rigorously, but utility limited, privacy assurance, and that adversarial perturbations continue to be a major vulnerability which can compromise even very accurate detection models. Escalating demands for trustworthy deployment of AI systems have come from regulatory frameworks like the General Data Protection Regulation (GDPR) and the European Union Artificial Intelligence Act, among other sources. The paper summarizes the elements of resilient AI-driven digital ecosystems and proposes a conceptual framework and research agenda for future research in this fast-moving space.
Keywords
Artificial Intelligence, Cybersecurity, Data Privacy, Intrusion Detection, Adversarial Machine Learning, Federated Learning, Differential Privacy, Explainable AI, GDPR, AI Governance
How to cite this paper
@article{1720158,
author = {Darshankumar Jaysukh Dhanani},
title = {Cybersecurity and Privacy Protection in AI-Driven Digital Environments},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {10},
number = {1},
pages = {2956-2967},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1720158.pdf},
abstract = {The rise of artificial intelligence (AI) has revolutionized the nature of cybersecurity, both in terms of its attack and defense capabilities, and also due to the new privacy threats that it poses. This paper reviews the literature systematically, and investigates the usage of AI technologies in the context of enhancing cyber-defence and safeguarding data privacy in AI-driven digital environments as well as their adverse usage and destabilisation by adversarial actors such as machine learning (ML), deep learning (DL), federated learning, and explainable AI (XAI). A total of 21 peer-reviewed and indexed sources have been analysed and thematically categorised into four areas: AI-based threat and intrusion detection, adversarial machine learning and model robustness, privacy-preserving AI techniques, and governance/regulatory compliance. The review reveals that, compared to signature-based approaches, AI can significantly improve accuracy of anomaly and intrusion detection, that federated learning and differential privacy provide mathematically rigorously, but utility limited, privacy assurance, and that adversarial perturbations continue to be a major vulnerability which can compromise even very accurate detection models. Escalating demands for trustworthy deployment of AI systems have come from regulatory frameworks like the General Data Protection Regulation (GDPR) and the European Union Artificial Intelligence Act, among other sources. The paper summarizes the elements of resilient AI-driven digital ecosystems and proposes a conceptual framework and research agenda for future research in this fast-moving space.},
keywords = {Artificial Intelligence, Cybersecurity, Data Privacy, Intrusion Detection, Adversarial Machine Learning, Federated Learning, Differential Privacy, Explainable AI, GDPR, AI Governance},
month = {July},
doi = {https://doi.org/10.64388/IREV10I1-1720158}
}