Federated Learning-Adaptive Gated Recurrent Unit is suggested, a Federated approach that combines a lightweight Gated Recurrent Unit (GRU) classifier with alternating adversarial fine-tuning on each client using FGSM and PGD, without any communication overhead, guaranteeing data-locality privacy through exchange of only model weights.
Abstract
Lightweight, privacy-aware and adversarial robust intrusion detection is required for the proliferation of Internet of Things (IoT) devices. In the Industrial Internet of Things (IIoT), centralized detectors can be compromised by adversarial perturbations via gradient-based attacks, making them susceptible to raw traffic. We suggest Federated Learning-Adaptive Gated Recurrent Unit (FL-AdGRU), a Federated approach that combines a lightweight Gated Recurrent Unit (GRU) classifier with alternating adversarial fine-tuning on each client using FGSM and PGD, without any communication overhead. A two-stage resampling scheme (UCAS-SMOTE) reduces the class-imbalance ratio from 4081:1 to ≈4:1, followed by 61 features being reduced to 40 by a mutual-information selector (MI-SelectK). Under this scenario, FL-AdGRU achieves 99.9% accuracy and 0.999 weighted F1 (+6.5 p.p. over the federated DNN baseline), with no loss of accuracy when facing clean attacks, and boosts Fast Gradient Sign Method FGSM/Projected Gradient Descent (PGD) robustness by +19.3/+19.0 p.p. at the same level of ϵ = 0.1, thus effectively balancing the accuracy–robustness trade-off. It is robust (97.8%/84.2% on UNSW-NB15) and generalizes well to UNSW-NB15, while decaying slowly in skeptical scenarios (≈99.9% weighted F1 for moderate skew, 93.9%/86.7% for severe). Assuring data-locality privacy through exchange of only model weights; defenses against inference attack are left for future work. FL-AdGRU, with a total communication of 43.8 MB (≈50× less than centralized training), is deployable on bandwidth-constrained IIoT networks.
With the proliferation of Internet of Things (IoT), critical infrastructures such as smart cities, industrial automation, precision healthcare, and intelligent transportation have seen a significant shift in their security landscape. As these critical infrastructures are increasingly depending on OneM2M standards for interoperability and scalable service management, they are simultaneously presenting a larger and more structured attack surface. One of the most serious and realistic threats in such scenarios is black-box adversarial attacks, in which an attacker can compromise Machine Learning (ML) and Deep Learning (DL)-based intrusion detection systems (IDS) without having prior knowledge of the ML/DL model's architecture, parameters, and training data. To mitigate such a critical challenge, we propose a multi-stage framework specific to OneM2M-based IoT networks that can effectively counter transfer-based and query-based black-box adversarial attacks. Our framework's effectiveness will be tested on a dataset of 1.25 million labeled network flows collected from Azure IoT Hub-based IoT devices over a 10-day period. We will test the robustness of our framework against three adversarial attacks: FGSM with $\varepsilon=0.05$, PGD with 40 iterations and step size 0.01, and C&W with L2 optimization and 1,000 iterations. The proposed pipeline consists of four different mechanisms: (1) adversarial training with the use of mixed clean and adversarial samples, (2) traffic sanitization to minimize malicious and/or suspicious traffic flows before processing by the Common Service Entity (CSE), (3) the use of a black-box adversarial detector based on feature transformation, and (4) the use of an ensemble-based IDS to make use of the results of the Random Forest, XGBoost, MLP, and 1D-CNN-based IDSs via majority voting. The experimental results show that the proposed Ensemble + multi-defense configuration results in 98.1% accuracy, 98.3% TPR, and 1.7% FNR. Most notably, the proposed Ensemble + multi-defense configuration results in an ASR of 11.2%, which is down by 86% compared to the 82.3% ASR achieved by the baseline IDS. Notably, the proposed framework results in limited overheads in terms of RTT (increased by 8 ms), CPU (increased by 17%), and RAM (increased by 1.6 GB).
Hamza Jamiri, A. Zyane· International Conference on...· 0 citations
—The proposed study suggests a to help cope with issues related to cybersecurity in Internet of Things and Industrial Internet of Things environments without compromising privacy. The proposed framework introduces several innovative features, such as federated learning with momentum-based optimization, adaptive differential privacy, trust verification via blockchain, and Byzantine-resilient aggregation, to enhance the security, scalability, and robustness of the system compared with traditional intrusion detection systems. It also integrates supervised classification with autoencoder-based anomaly detection to detect existing and emerging cyberattacks. The proposed system was assessed with respect to the extended Industrial Internet of Things Intrusion Dataset (X-IIoT) and Network-Based Botnet Attack detection for IoT (N-BaIoT) benchmark datasets, where the environments were simulated as federated ones. The accuracy of the Hybrid Robust Federated Intrusion Detection System increased to 97.15% on X-IIoT and 97.64% on N-BaIoT with only 41 communication rounds and was resilient against up to 20% of Byzantine clients. These results showcase its efficacy to secure, private and communication-efficient intrusion detection for next generation Internet of Things and Hybrid Robust Federated Intrusion Detection System networks.
The proliferation of Internet of Things (IoT) devices has amplified the attack surface for large-scale cyber threats, with rapidly evolving malware families such as Mirai posing significant detection challenges. Existing side-channel and host-based approaches are limited by poor generalization to unseen variants and the absence of robust privacy protections during training. In this paper, we propose SecShield, a federated deep learning framework for privacy-preserving malware detection in resource-constrained IoT environments. SecShield employs a three-party secure computation model, where clients locally train a shared deep neural network on power side-channel traces and transmit only noisy parameter updates to a central server via an aggregator, preventing raw data exposure. Differential privacy is incorporated by injecting calibrated noise into gradients, mitigating inference risks such as data reconstruction and poisoning attacks. This decentralized architecture enables continuous adaptation to zero-day malware, reduces communication overhead, and ensures robustness against adversarial manipulation. Experimental evaluations on IoT power trace datasets demonstrate that SecShield achieves high detection accuracy over 98% while preserving client data confidentiality and maintaining computational efficiency.
Damodar Dhital, Sabir Ahmed Khan, A.L.M.U.S.T.A.P.H.A.A. Wakili et al.· International Conference on...· 0 citations
A constraint-aware adversarially robust Internet of Things (IoT) traffic classification system with protocol validity, device behavior consistency, and manifold-aware training and evaluation is presented, demonstrating improved robustness, realism, and deployability compared to existing approaches.
Vehicular networks are a continuation of vehicle-to-everything (V2X) communication, which is becoming the foundation of intelligent transportation systems and allows vehicles, roadside units, and grid infrastructure to communicate reliably. Nevertheless, the decentralized aspect of V2X renders it very susceptible to adversarial cyberattacks, both on a large scale such as DDoS attacks, spoofing, and Sybil attacks. Conventional centralized intrusion detection systems (IDSs) have limitations in terms of latency, bandwidth overhead, and privacy risks. In this study, we introduce a Differentially Private Federated Adversarial Learning (DP-FAL) model that integrates federated learning to train decentralized models with adversarial defence schemes and differential privacy tools to address gradient leakage. The proposed DP-FAL framework achieves a detection accuracy of 94.2% and a communication overhead reduction of up to 23%. This shows that it can be used in bandwidth-limited and latency-sensitive V2X systems because of its ability to ensure high detection reliability with low communication costs. The suggested DP-FAL model is a privacy-conserving, scalable, and robust intrusion prevention system that can be used real-time V2X conditions. These results indicate that DP-FAL has the potential to be deployed safely, reliably, and sustainably in next-generation transportation systems.
S. Sonker, V. K. Raina, B. B. Sagar et al.· Discover Computing· 0 citations
Federated Learning (FL) enables privacy-preserving collaborative model training for Unmanned Aerial Vehicles (UAVs). However, its decentralized nature makes it vulnerable to adversarial attacks such as model poisoning, label flipping, and backdoor attacks. To address these challenges in resource-constrained UAV environments, this study proposes ResFL-UAV++, a lightweight and secure FL framework incorporating a multi-layer defense mechanism. The framework integrates a multi-metric anomaly detection module based on cosine similarity, L2-Norm Filtering, and Temporal Update Consistency (TUC) to identify malicious UAV updates. A hybrid robust aggregation strategy combining Trimmed Mean and Krum mitigates adversarial effects while preserving model convergence. Additionally, adversarial training using the Fast Gradient Sign Method (FGSM), together with Differential Privacy (DP), enhances reliability and data confidentiality while incurring minimal computational overhead. Experimental evaluation on the HIT-UAV Infrared Thermal dataset and the WebUAV-3M demonstrates that ResFL-UAV++ achieves 98% accuracy under adversarial conditions. The framework reduces the Backdoor Attack Success Rate (ASR) to below 20%. Furthermore, it achieves over 98% accuracy in adversarial UAV detection while introducing less than 4% system overhead. These results demonstrate the effectiveness and practicality of ResFL-UAV++ for secure FL in UAV environments.
S. Sophia, P. G. Jeba Leelipushpam, T. Jebaseeli· Frontiers of Computer Scienc...· 0 citations