arXiv subjects

Saadat Izadi

Publications and source records attributed to Saadat Izadi.

6 recordsLinked to original sources

arXiv2026

MRC-GAT: A Meta-Relational Copula-Based Graph Attention Network for Interpretable Multimodal Alzheimer's Disease Diagnosis

Alzheimer's disease (AD) is a progressive neurodegenerative condition necessitating early and precise diagnosis to provide prompt clinical management. Given the paramount importance of early diagnosis, recent studies have increasingly focused on computer-aided diagnostic models to enhance precision and reliability. However, most graph-based approaches still rely on fixed structural designs, which restrict their flexibility and limit generalization across heterogeneous patient data. To overcome these limitations, the Meta-Relational Copula-Based Graph Attention Network (MRC-GAT) is proposed as an efficient multimodal model for AD classification tasks. The proposed architecture, copula-based similarity alignment, relational attention, and node fusion are integrated as the core components of episodic meta-learning, such that the multimodal features, including risk factors (RF), Cognitive test scores, and MRI attributes, are first aligned via a copula-based transformation in a common statistical space and then combined by a multi-relational attention mechanism. According to evaluations performed on the TADPOLE and NACC datasets, the MRC-GAT model achieved accuracies of 96.87% and 92.31%, respectively, demonstrating state-of-the-art performance compared to existing diagnostic models. Finally, the proposed model confirms the robustness and applicability of the proposed method by providing interpretability at various stages of disease diagnosis.

cs.LG↗

arXiv2026

ASA: Adaptive Smart Agent Federated Learning via Device-Aware Clustering for Heterogeneous IoT

Federated learning (FL) has become a promising answer to facilitating privacy-preserving collaborative learning in distributed IoT devices. However, device heterogeneity is a key challenge because IoT networks include devices with very different computational powers, memory availability, and network environments. To this end, we introduce ASA (Adaptive Smart Agent). This new framework clusters devices adaptively based on real-time resource profiles and adapts customized models suited to every cluster's capability. ASA capitalizes on an intelligent agent layer that examines CPU power, available memory, and network environment to categorize devices into three levels: high-performance, mid-tier, and low-capability. Each level is provided with a model tuned to its computational power to ensure inclusive engagement across the network. Experimental evaluation on two benchmark datasets, MNIST and CIFAR-10, proves that ASA decreases communication burden by 43% to 50%, improves resource utilization by 43%, and achieves final model accuracies of 98.89% on MNIST and 85.30% on CIFAR-10. These results highlight ASA's efficacy in enhancing efficiency, scalability, and fairness in heterogeneous FL environments, rendering it a suitable answer for real-world IoT apps.

cs.NI↗

arXiv2026

Adaptive Meta-Aggregation Federated Learning for Intrusion Detection in Heterogeneous Internet of Things

The rapid proliferation of the Internet of Things (IoT) has brought remarkable advancements to industries by enabling interconnected systems and intelligent automation. However, this exponential growth has also introduced significant security vulnerabilities, making IoT networks increasingly targets for sophisticated cyberattacks. The heterogeneity of IoT devices poses critical challenges for traditional intrusion detection systems. To address these challenges, this paper proposes an innovative method called Adaptive Meta-Aggregation Federated Learning (AMAFed), designed to enhance intrusion detection in heterogeneous IoT networks. By employing a dynamic weighting mechanism using meta-learning, AMAFed assigns adaptive importance to local models based on their data quality and contributions, enabling personalized yet collaborative learning across devices. The proposed method was evaluated on three benchmark IoT datasets: ToN-IoT, N-BaIoT, and BoT-IoT, representing diverse real-world scenarios. Experimental results demonstrate that AMAFed achieves detection accuracy up to 99.8% on ToN-IoT, with F1-scores exceeding 98% across all datasets. On the N-BaIoT dataset, it reaches 99.88% accuracy, and on BoT-IoT, it achieves 98.12% accuracy, consistently outperforming state-of-the-art approaches.

cs.NI↗

arXiv2026

Lightweight Cluster-Based Federated Learning for Intrusion Detection in Heterogeneous IoT Networks

The rise of heterogeneous Internet of Things (IoT) devices has raised security concerns due to their vulnerability to cyberattacks. Intrusion Detection Systems (IDS) are crucial in addressing these threats. Federated Learning (FL) offers a privacy-preserving solution, but IoT heterogeneity and limited computational resources cause increased latency and reduced performance. This paper introduces a novel approach Cluster-based federated intrusion detection with lightweight networks for heterogeneous IoT designed to address these limitations. The proposed framework utilizes a hierarchical IoT architecture that encompasses edge, fog, and cloud layers. Intrusion detection clients operate at the fog layer, leveraging federated learning to enhance data privacy and distributed processing efficiency. To enhance efficiency, the method employs the lightweight MobileNet model alongside a hybrid loss function that integrates Gumbel-SoftMax and SoftMax, optimizing resource consumption while maintaining high detection accuracy. A key feature of this approach is clustering IoT devices based on hardware similarities, enabling more efficient model training and aggregation tailored to each cluster's computational capacity. This strategy not only simplifies the complexity of managing heterogeneous data and devices but also improves scalability and overall system performance. To validate the effectiveness of the proposed method, extensive experiments were conducted using the ToN-IoT and CICDDoS2019 datasets. Results demonstrate that the proposed approach reduces end-to-end training time by 2.47x compared to traditional FL methods, achieves 2.16x lower testing latency, and maintains exceptionally high detection accuracy of 99.22% and 99.02% on the ToN-IoT and CICDDoS2019 datasets, respectively.

cs.NI↗

arXiv2026

CF-HFC:Calibrated Federated based Hardware-aware Fuzzy Clustering for Intrusion Detection in Heterogeneous IoTs

The rapid expansion of heterogeneous Internet of Things (IoT) environments has heightened security risks, as resource-constrained devices remain vulnerable to diverse cyberattacks. Federated Learning (FL) has emerged as a privacy-preserving paradigm for collaborative intrusion detection; however, device and data heterogeneity introduce major challenges, including straggler delays, unstable convergence, and unbalanced error rates. This paper presents a Calibrated Federated Learning method with Hardware-aware Fuzzy Clustering (CF-HFC) to enhance intrusion detection performance in heterogeneous IoT networks. The proposed three-tier Edge-Fog-Cloud architecture integrates three complementary components: (1) hardware-aware fuzzy clustering, which organizes clients by computational capacity to mitigate straggler effects; (2) Fuzzy-FedProx aggregation, which stabilizes optimization under non-IID data distributions; and (3) Adaptive Conformal Calibration (ACC), which dynamically adjusts decision thresholds to balance false negative and false positive rates. Extensive experiments on ToN-IoT, BoT-IoT, Edge-IIoTset, and CICDDoS2019 datasets demonstrate that CF-HFC outperforms baseline methods such as FedAvg and FedProx, achieving over 99% detection accuracy, faster convergence, and lower communication latency. Overall, the results verify that CF-HFC effectively mitigates both device- and data-level heterogeneity, compared to existing federated learning approaches, providing accurate and efficient intrusion detection across Heterogeneous IoTs environment.

cs.NI↗

arXiv2025

Mist-Assisted Federated Learning for Intrusion Detection in Heterogeneous IoT Networks

The rapid growth of the Internet of Things (IoT) offers new opportunities but also expands the attack surface of distributed, resource-limited devices. Intrusion detection in such environments is difficult due to data heterogeneity from diverse sensing modalities and the non-IID distribution of samples across clients. Federated Learning (FL) provides a privacy-preserving alternative to centralized training, yet conventional frameworks struggle under these conditions. To address this, we propose a Mist-assisted hierarchical framework for IoT intrusion detection. The architecture spans four layers: (i) Mist, where raw data are abstracted into a unified feature space and lightweight models detect anomalies; (ii) Edge, which applies utility-based client selection; (iii) Fog, where multiple regional aggregators use FedProx to stabilize training; and (iv) Cloud, which consolidates and disseminates global models. Evaluations on the TON-IoT dataset show the framework achieves 98-99% accuracy, PR-AUC> 0.97, and stable convergence under heterogeneous and large-scale settings, while maintaining efficiency and preserving privacy.

cs.NI↗