Federated learning and edge computing-based collaborative detection system for IoT anomaly behavior

Enhanced Intrusion Detection in IoT Networks using Federated Learning

Existing Federated intrusion detection system (IDS) solutions unfittingly deploy homogeneous models across all devices regardless of resource constraints, lack real-time detection capabilities due to synchronous federated rounds, and fail to balance the trade-off between lightweight edge processing and deep analytical accuracy. This paper addresses these through intelligent workload distribution between edge and cloud layers. The system uses a dual-detection mechanism where lightweight Decision Tree (DT) models on IoT devices provide immediate threat classification with confidence scoring. High-confidence predictions enable instant response to attacks without waiting for the server, while uncertain cases are sent to a CNN-LSTM model for deep analysis. In the federated learning component, edge devices share only model corrections from server feedback rather than continuous parameter updates. The central server aggregates these learning experiences to refine a global model and redistributes the updates back to edge devices. This selective knowledge sharing reduces communication overhead while enabling continuous improvement of local models and ensuring privacy. The performance of the system was evaluated using the IoT-23 dataset. Our approach achieved an accuracy of 98.08% on edge detection and 95.27% in the overall asynchronous setup. These results show a success in implementing a real time, scalable, privacy-preserving, and adaptive IDS in large-scale IoT deployments.

Dynamic anomaly detection in IoT environments: a multi-model machine learning approach

Quantum machine learning-based intrusion detection system for IoT cloud-enabled smart city environments

The fast integration of Internet of Things (IoT) devices and cloud platforms has altered current smart cities, allowing for intelligent services and effective communication. However, the increased interconnectedness has broadened the attack surface, exposing systems to complex, evolving cyberattacks that standard Intrusion Detection Systems (IDSs) cannot adequately counter. Classical Machine Learning architectures have constraints in handling high-dimensional data, achieving scalability, maintaining performance, and adapting to dynamic attack behaviours. To find these problems, this study presents a Quantum Machine Learning (QML)-based Intrusion Detection framework that uses Quantum Support Vector Machines (QSVM) to improve detection accuracy, adaptability, and computational efficiency in conceptual IoT Cloud-Enabled Smart City environments. The proposed model was assessed through simulation-based evaluation on the CICDDoS2019 dataset using the DrDoS DNS subset and compared against conventional Machine Learning Models such as SVM, XGBoost, Random Forest, and RNN. The experimental results show an overall performance improvement of 99.28%, with our research delivering significantly higher detection accuracy and system adaptability, along with fewer false alarms and faster response times. These results demonstrate the efficiency of Quantum-enhanced Learning in protecting IoT-Cloud infrastructures in smart-city environments. The proposed QSVM framework was evaluated using a classical quantum simulation environment. Therefore, the reported findings represent simulation-based observations and should not be interpreted as evidence of practical quantum computational advantage or hardware-based validation.

Adaptive Three-Tier Federated Intelligence for Real-Time Anomaly Detection and Threat Prediction in Resource-Constrained IoT Systems

The blistering development of the Internet of Things (IoT) systems has made them more vulnerable to the cyber threat, especially when it comes to resources and the decentralization of data production. This paper suggests a three-level federated intelligence model, which is flexible in real-time anomaly detection and predictive threat analysis of IoTs. The model combines on-device lightweight detection, edge-level federated learning and cloud-based global optimization to facilitate privacy-preserving and scalable security. A resource conscious adaptive feature selection system is used to dynamically scale the computational complexity, and a time prediction algorithm used to predict early threats. To ensure realistic validation of the model in various attack scenarios, benchmark IoT intrusion detection datasets are used to evaluate the model, which are widely used in federated anomaly detection research. The experimental evidence indicates that the offered method can reach the accuracy of 96.8% and F1-score of 96.0% and decrease the volume of communication by 85% and the execution time to 18 ms, instead of 42 ms. Moreover, the prediction module attains 93.7% accuracy and has a lead time of 6.8 seconds. These results point to the proposed framework as being a successful balance of accuracy, efficiency, and scalability to real-world IoT security applications.

An Iot-Integrated Federated Edge Computing Paradigm for Privacy-Preserving Smart Campus Infrastructure

The rise in the use of the Internet of Things is resulting in extensive and varied data being generated on university campuses, especially in the domain of energy consumption and management in buildings. Conventional learning algorithms will fail in this scenario because they are restricted by privacy boundaries and communication cost considerations on edge devices. Against this background, we introduce a federated learning framework on campus. In which learning will occur at the edge nodes collaboratively. This scheme provides a resource-conscious multi-layer federating strategy that controls the number of devices taking part in the process as well as the frequency at which aggregation is done based on each device’s capability. Contrary to existing federating designs that assume each edge node is similar in ability, this design considers the differences in each campus environment. The experiments conducted using the realistic smart campus test bed reveal that our approach ensures stronger convergence, reduced communication overhead, as well as more accurate predictions of energy consumption, when compared to traditional Federated Averaging as well as the fixed aggregation strategy. Moreover, the approach allows for simplicity in the preservation of privacy, without losing scalability, especially for the smart campus setting that has been projected to be rather large.

An Explainable Ensemble Feature Selection Framework for Enhanced IoT Edge Attack Detection

—Intrusion detection systems (IDS) deployed on edge-network devices are rapidly increasing as the edge computing approach is widely applied in network infrastructure. Despite the advantages that edge computing offers, enhanced network performance in terms of latency, bandwidth consumption, and privacy, there have remained challenges related to the constrained resources of edge devices. In machine learning-based IDS systems, to deal with large, noisy, or strong feature correlations in practical IoT data, dimensionality reduction methods are often applied to generate efficient inputs for machine learning models. However, a major challenge is enhancing both the performance and explainability of the edge IDS system to meet the requirements of the security field. To overcome the challenge, we propose an explainable hybrid feature-selection framework (X-EFS) that combines multiple feature reduction techniques via a multi-expert system module, then uses the MDA metric to select the most important features, ensuring high performance and explainability. Evaluations on the CICIoT2023 dataset indicate that condensing the feature space from 46 to 6 dimensions yields an Accuracy of 98.33% and an F1-score of 98.54% across a 5-fold stratified validation. This extreme dimensionality reduction directly mitigates inference latency and memory overhead, satisfying edge-constrained deployment requirements without compromising detection capacity or intrinsic explainability.