Answers are grounded in this paper and cite their sources.
This paper presents an artificial intelligence (AI)-driven, privacy-by-design framework for managing personal data in heterogeneous Internet of Things (IoT) environments. The framework integrates supervised learning for privacy risk estimation with reinforcement learning for adaptive control of data sharing, retention, and access behaviours at the device and edge layers. A dataset of 10,000 anonymised incidents from the Indian Computer Emergency Response Team (CERT-In), the National Institute of Standards and Technology (NIST), and the European Union Agency for Cybersecurity (ENISA) (2020–24), supplemented by controlled multi-device simulations, was used to evaluate the system under varied operational contexts. The study assesses privacy preservation, usability impact, and computational performance using explicitly defined and reproducible metrics. The adaptive approach reduced simulated privacy breach events by 25 per cent relative to a fully specified static baseline and maintained acceptable latency and usability levels. By translating the European Union (EU) General Data Protection Regulation (GDPR) principles such as data minimisation, purpose limitation, and accountability into quantifiable indicators, the framework demonstrates how privacy-by-design can be operationalised in real time. The findings provide a practical foundation for regulators, data protection officers (DPOs), and IoT developers seeking verifiable, context-aware privacy enforcement mechanisms. This article is also included in The Business & Management Collection which can be accessed at https://hstalks.com/business/.
No takes yet. Share an insight, caveat, or question.
Kumar et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: