Privacy-Preserving Federated Intrusion Detection for Distributed IoT Environments: A Critical Review of Mechanisms, Threats and Open Research Gaps
📑 Paper Information
| 📑 Paper Title | Privacy-Preserving Federated Intrusion Detection for Distributed IoT Environments: A Critical Review of Mechanisms, Threats and Open Research Gaps |
| 👤 Authors | Sujata Pattnaik, Dr. Ridhika Sidhi |
| 📘 Published Issue | Volume 1 Issue 5 |
| 📅 Year of Publication | 2026 |
| 🆔 Unique Identification Number | IJCSED-V1I5P6 |
📝 Abstract
The rapid expansion of the Internet of Things (IoT) has produced large, heterogeneous and geographically dispersed networks whose devices differ in hardware capability, communication pattern and exposure to attack. Machine-learning-based intrusion detection systems (IDS) can recognise malicious traffic in such networks, but conventional designs depend on collecting raw traffic at a central server, which increases privacy exposure, communication load and the risk of a single high-value data repository. Federated learning (FL) offers an alternative in which IoT devices, gateways or edge nodes train a shared detection model while keeping raw traffic local. This paper presents a structured critical review of privacy-preserving federated intrusion detection for distributed IoT environments. It first characterises the IoT security setting and the main families of intrusion detection. It then examines representative federated IDS studies and recent surveys, analyses the privacy mechanisms used to protect model updates—differential privacy, secure aggregation, homomorphic encryption, encrypted communication and authentication—and describes the threats that target the federated learning process itself, including information leakage and model poisoning. The review shows that privacy, data heterogeneity, communication cost and robustness are usually studied in isolation, that privacy guarantees are rarely reported together with detection utility, and that many evaluations rely on simplified client partitions. Building on this analysis, the paper derives a set of research gaps and maps them to concrete research objectives and directions for an integrated, measurable and resource-aware federated IDS for IoT.
📝 How to Cite
Sujata Pattnaik, Dr. Ridhika Sidhi, "Privacy-Preserving Federated Intrusion Detection for Distributed IoT Environments: A Critical Review of Mechanisms, Threats and Open Research Gaps" International Journal of Computer Science and Engineering Development, V1(5): Page(43-52) November - December 2026. ISSN: 3139-0862. www.ijcsed.com. Published by Scientific and Academic Research Publishing.
