F-ACVAE: A Federated Adaptive Conditional Variational Auto-Encoder for Privacy-Preserving Intrusion Detection in IoT Networks
2026-07-06 • Machine Learning
Machine LearningCryptography and Security
AI summaryⓘ
The authors address the problem of detecting cyber-attacks on IoT devices without sharing sensitive data by creating a new collaborative learning method called F-ACVAE. Their approach allows many devices to train a model together while keeping parts of it private, which helps handle tricky data differences and imbalances. They also designed a way to smoothly combine updates from different devices to keep the model stable. Testing on a real IoT dataset showed their method is very accurate and cuts communication needs significantly, making it good for devices with limited resources.
Internet of Things (IoT)Intrusion Detection System (IDS)Federated LearningVariational AutoencoderNon-IID DataClass ImbalanceSelective Parameter AggregationClient DriftCommunication EfficiencyCybersecurity
Authors
Mohammad Ansarimehr, Somayeh Changiz, Ehsan Baghishani, Ali Mousavi
Abstract
The rapid proliferation of Internet of things (IoT) devices has significantly expanded the cyber-attack surface, necessitating robust and privacy-preserving intrusion detection systems (IDS). However, centralized learning approaches often suffer from severe performance degradation due to high-dimensional traffic data, extreme class imbalance, and highly non-independent and identically distributed (non-IID) data across heterogeneous edge devices. To address these challenges, this paper proposes F-ACVAE, a federated adaptive conditional variational autoencoder framework that enables collaborative model training across distributed IoT devices without sharing raw data. F-ACVAE incorporates selective parameter aggregation, where local encoders remain private while globally shared components are synchronized to preserve discriminative latent structures. To further enhance stability under extreme non-IID settings and feature distribution shifts, we introduce a novel constrained momentum Gaussian aggregation (CMGA) strategy that combines update clamping with momentum-based smoothing to mitigate client drift. Extensive experiments on the N-BaIoT dataset demonstrate that F-ACVAE achieves an average accuracy and macro F1-score of 99\%, outperforming state-of-the-art baselines. Moreover, the selective aggregation mechanism reduces communication overhead by approximately 62\%, making the framework particularly suitable for resource-constrained IoT environments. These results highlight the effectiveness of F-ACVAE in achieving high detection performance while ensuring privacy preservation and communication efficiency.