Federated Bandit Intrusion Detection (FBID), a novel adaptive PFL framework to address this limitation through server-side personalization control, employs a contextual multi-armed bandit at the server to dynamically regulate each client's local training intensity according to its observed behavior and update quality.
Abstract
Personalized Federated Learning (PFL) has emerged as a promising solution for intrusion detection in heterogeneous IoT environments, as it can improve local adaptation under highly Non-Independent and Identically Distributed (non-IID) data distributions. However, existing PFL methods often rely on client-side self-adjustment, which may lead to over-personalization and substantial degradation in out-of-distribution (OOD) attack detection. In this paper, we propose Federated Bandit Intrusion Detection (FBID), a novel adaptive PFL framework to address this limitation through server-side personalization control. In particular, FBID employs a contextual multi-armed bandit at the server to dynamically regulate each client's local training intensity according to its observed behavior and update quality. Moreover, FBID introduces a trust-based blending mechanism to derive client-specific interpolation coefficients between the global and local models, thereby preserving global attack-detection knowledge while still allowing beneficial local specialization. Through extensive experiments on the CICIoT2023 dataset under heterogeneous client distributions and OOD stress-test settings, we show that FBID improves individual client OOD Detection Rate (DR) by up to 7.66% and F1-Score (F1) by up to 5.08% (relative) over the strongest stable baseline, while also improving robustness to previously unseen attack classes.
The outcomes of these experiments prove that, in the context of federated IDS for a heterogeneous IoT network, the integration of trust-aware aggregation with contrastive representation learning and imbalance-aware optimization can enhance performance.
Federated learning (FL) is a promising paradigm for privacy-preserving IoT intrusion detection, but its effectiveness can be substantially degraded by the combination of heterogeneous non-IID client distributions and severe multi-class imbalance. Under such conditions, conventional size-based aggregation may overemphasize large yet highly skewed clients, limiting the representation of minority attack classes in the global model. To address this issue, we propose Mean/Std, a lightweight distribution-aware aggregation strategy that combines a client-size proxy with two complementary statistics of local label distributions, namely the standard deviation and the dominance gap of class proportions, while preserving a communication footprint comparable to FedAvg. Experiments on the N-BaIoT benchmark, comprising seven heterogeneous IoT clients and eleven traffic classes, are conducted under a privacy-oriented update-perturbation setting inspired by secure aggregation workflows. The results show that Mean/Std consistently provides the strongest imbalance-aware performance among the evaluated FL baselines, achieving a Macro-F1 score of 0.8418 and a Balanced Accuracy of 0.8722 while improving the representation of minority attack classes. Additional experiments across five independent random seeds and a comprehensive hyperparameter sensitivity analysis further confirm the robustness and stability of the proposed aggregation mechanism. Overall, the results demonstrate that lightweight distribution-aware aggregation offers an effective, robust, and practically deployable solution for mitigating aggregation bias under simultaneous non-IID heterogeneity and severe multi-class imbalance in FL-based IoT botnet detection.
Yassine El Yamani, Youssef Baddi, Najib El Kamoun· IoT· 0 citations
The results show a success in implementing a real time, scalable, privacy-preserving, and adaptive IDS in large-scale IoT deployments through intelligent workload distribution between edge and cloud layers.
Chidera Winifred John, Eduediuyai Ekerete Dan, P. Asuquo et al.· E3S Web of Conferences· 0 citations
: Federated Learning (FL) has emerged as a promising approach to build collaborative Intrusion Detection Systems (IDSs) in the IoT, e.g., in smart homes. FL allows models to be shared without exposing sensitive training data, thus protecting the privacy of IoT users. However, existing FL-based IDSs rely on assumptions that rarely hold in practice, namely homogeneous devices, synchronous participation, and benign contributors. We argue that, in real-world smart homes, IoT devices are highly heterogeneous, resource-constrained, and attractive targets for adversaries, which makes conventional FL less effective or vulnerable to poisoning attacks. We present H OME G UARD , a collaborative IDS specifically designed for the constraints and threat model of practical smart home IoT infrastructures. In our approach, we rethink FL deployment by (1) of-floading model training to gateways to manage computational heterogeneity of IoT devices and (2) organizing anomaly detection models into device-specific communities based on privacy-preserving traffic fingerprints which do not expose sensitive data. Within communities and across smart homes, H OME G UARD implements an asynchronous, hierarchical FL architecture that tolerates device churn, uneven data availability, and Byzantine participants. Further, H OME G UARD applies Byzantine-robust aggregation at two levels: within local communities, and globally in the cloud to limit the impact of compromised devices. Experimental evaluation shows that H OME G UARD achieves an average true positive rate of 97.86% locally and 97.53% globally with a 0% false positive rate, while maintaining robustness against both targeted and untargeted poisoning attacks.
Philipp Eichhammer, Christian Berger, Hans P. Reiser· Proceedings of the 23rd Inte...· 0 citations
AF-BKM is presented, an Adaptive Federated Baseline K-Means that repairs the federated mechanism with two label-free, statistics-only enhancements, and identifies merge-induced precision decay under non-IID workers as an open gap.
Mohammed I. Al-Saleh, Joseph Azar· IoT· 0 citations
Federated Learning has become a practical approach for training intrusion detection models across distributed Internet of Things devices, but it remains exposed to poisoning attacks, non-IID data heterogeneity, and free-rider exploitation. This paper presents DT-Guard, a defense framework that leverages a server-side Digital Twin as a controlled testing environment for actively verifying client model behavior. Each submitted update is deployed in the Digital Twin and evaluated on synthetic challenge data through a four-layer pipeline that examines detection capability, backdoor resistance, parameter deviation, and cross-round stability. A complementary aggregation scheme called DT-Driven Performance Weighting compares client predictions against the current global model, exposing free-riders whose outputs are nearly indistinguishable from the global baseline. We validate DT-Guard on CIC-IoT-2023 under five poisoning strategies. DT-Guard generally outperforms nine existing defenses in accuracy, false positive rate, and contribution fairness.
H. Pham, Duy The Phan, Van-Hau Pham· IEEE International Conferenc...· 0 citations