Skip to content
Conference Open access

A Privacy-Aware Federated Tabnet Framework for Intelligent Intrusion Detection in Secure IoT Architectures

Sep 2026 · 2026 International Conference on Secure IoT and Cybersecurity (ICOSICS) · pp. 567-574 · 0 citations · 22 references

TL;DR

A Privacy-Aware Federated TabNet framework combining Federated Learning, Differential Privacy and TabNet to facilitate intelligent and Privacy-preserving intrusion detection in secure IoT architectures is introduced.

Abstract

The proliferation of the Internet of Things (IoT) has led to a larger number of smart devices being connected and interconnected, thus leaving distributed systems vulnerable to new and sophisticated cyber attacks and causing serious concerns about data privacy and secured information sharing. Traditional IDSs are mostly relying on centralized learning methods, in which raw network data is delivered to central servers and this raises the risk of privacy leakage and diminishes the scope of its use in privacy sensitive IoT settings. In this regard, this paper introduces a Privacy-Aware Federated TabNet framework combining Federated Learning, Differential Privacy and TabNet to facilitate intelligent and Privacy-preserving intrusion detection in secure IoT architectures. The proposed framework allows for decentralized collaborative learning by storing data on local clients and safeguarding model updates by employing Differential Privacy. The framework is tested against the Edge-IIoTset dataset consisting of around 3.1 million network traffic packets from 15 classes of normal and multiple cyberattacks. Results on the experimental data sets show that the proposed framework is able to obtain an overall accuracy of 94.90%, which surpasses multiple baseline models such as the traditional machine learning and deep learning baseline models with the goodness of maintaining strong privacy guarantees and having good generalization performance. This research's main novelty is an effective combination of privacy-preserving federated learning with an interpretable TabNet-classifier that creates a scalable, secure, and efficient intrusion detection system for next-generation distributed IoT devices.

Read PDF

Similar papers

Conference Open access Sep 2026

A Federated Learning Framework for Privacy-Aware Intrusion Detection (PAID) for Internet of Medical Things

The proposed PAID model achieves better detection results, with 97.9% accuracy for binary classification and 95.6% accuracy for multi-class classification, achieving higher accuracy than the conventional machine learning and centralised deep learning approaches, and maintaining data privacy and scalability in distribut...

S. S, S. K, Almas Begum · 0 citations
Open access 2026

A Federated Semi-Supervised Framework for Data Efficiency and Privacy-Preserving Intrusion Detection in Internet of Things

The Internet of Things (IoT) forms the foundation of modern smart environments, enabling intelligent industries, homes, cities, healthcare, and autonomous systems. However, as IoT devices increasingly connect to cloud platforms and the Internet, they become highly vulnerable to network intrusions that can lead to criti...

Yi-Fan Zeng, Zi-Hui Gu, Pei-Jia Zheng et al. · 0 citations
Open access Sep 2026

Privacy-Preserving Intrusion Detection using Federated Learning in Distributed Networks

A privacy-friendly intrusion detection system (PP-IDS) that operates on the basis of conjoint learning, which makes PP-IDS suitable for cloud services, edge devices, Internet of Things networks or business systems – basically anywhere that data needs to remain private.

Ram Chouhan · 0 citations
Conference Open access 2026

Scalable and Efficient Security Solutions for IoT Networks: An Adaptive Machine Learning Approach

The number of Internet of Things (IoT) devices has grown at a rapid pace and has created a larger attack surface for modern networks, making them an appealing target for botnets, ransomware, and distributed denial-of-service (DDoS) attacks. While traditional IDSs are typically built with a centralized machine learning...

J. J. Patil, Prajakta Shirke · 0 citations
#graph neural networks Open access Oct 2026

Trust-Aware Federated Learning for Privacy-Preserving IoT Intrusion Detection

FLZT-IDS (Federated Learning with Zero-Trust for Intrusion Detection in IoT) employs gradient-deviation monitoring to mitigate the effects of heterogeneous client updates, while Graph Neural Networks and an Attention-based BiLSTM capture relational and temporal attack patterns.

Santosh Kumar Banbhrani, Chengyongxiao Wei, Muhammad Asad · 0 citations
Open access Sep 2026

A novel FedLLM intrusion detection framework for privacy-preserving security in IoT enabled smart city network

The proliferation of Internet of Things (IoT) devices in Smart City infrastructures has introduced unprecedented opportunities for automation, healthcare, and transportation, while simultaneously exposing the ecosystem to complex and multi-dimensional cyberattacks. Conventional intrusion detection systems (IDS) either...

Shakila Basheer, G. Aldehim, A. Alluhaidan et al. · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.