Jul 2026· International Conference Computing Methodologies and Communication· pp. 499-506· 0 citations· 16 references
Abstract
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.
This paper introduces an innovative ML-based security paradigm that improves the attack detection accuracy by combining adaptive feature extraction techniques with a context-attentive hybrid mechanism and maximizes detection accuracy and computational efficiency.
P. P. Bairagi, Ashish Bagwari, Sailen Dutta Kalita et al.· international journal of eng...· 0 citations
The rapid growth of the Internet of Things (IoT) has intensified cybersecurity risks while exposing the limitations of traditional security solutions in resource-constrained environments. Intrusion detection in IoT systems, therefore, requires reliable, real-time decision-making with minimal computational overhead. This paper presents a lightweight IoT security decision framework that combines entropy-guided feature selection with an adaptive ensemble-based intrusion detection strategy. The proposed approach employs an entropy–correlation (EnCor) feature selection pipeline to construct a compact and informative feature subset, reducing complexity while preserving discriminative security characteristics. Detection decisions are generated using a soft voting ensemble of complementary machine learning classifiers, supported by an adaptive fallback mechanism to improve reliability under diverse attack scenarios. The framework is specifically designed for edge- and gateway-level IoT deployment, avoiding the high latency and computational demands associated with deep learning and blockchain-based solutions. Experimental evaluation on the TON_IoT and CICIoT2023 datasets demonstrates high detection accuracy with low inference latency and reduced memory consumption. The results confirm that effective intrusion detection can be achieved without compromising practical deployment feasibility. Overall, the proposed framework establishes intrusion detection as an efficient and deployable security decision layer for real-world IoT environments.
Saif Wali Ali Alsudani, M. Feizi-Derakhshi· International Journal of Ele...· 0 citations
The rapid expansion of the Internet of Things (IoT) has raised additional concerns about security, and there was a major risk of Distributed Denial-of-Service (DDoS) attacks because the IoT devices have limited computation, memory, and energy capabilities. Traditional intrusion detection methods, which are at times contrived to support a high capacity, are incompetent at these limitations, delaying detections, having too many false alarms, and also compromising the system performance. This study offers a resource-efficient, adaptive machine learning system that was suitable to be used in the operation of DDoS attacks in resource-confined IoT settings. The technique combines the hybrid feature selection algorithms based on mutual information gain and recursive feature elimination to construct a more compact and high-utility feature set together with the optimization of the lightweight classifiers, including stochastic gradient descent and shallow decision trees. The concept drift was solved by an online incremental learning mechanism that guarantees long-term trend detection over time against changing patterns of attacks. The evaluation of the benchmark datasets (CICDDoS2019, BoT-IoT, TON_IoT) using experimental evaluation on a heterogeneous testbed IoT and assessing both security metrics and resource efficiency was researched. The model suggested had a precision of 0.973, a recall of 0.959, an F1-score of 0.966, and an average decrease of malicious traffic by 93 percent at the expense of legitimacy throughput. Latency was decreased to 2.6 seconds when detecting high-intensity attacks, and the CPU and memory usage continued to be less than 35 percent and 70 percent of the device capacity, respectively. A better result in terms of accuracy, response time, false positive rates, and not using resource budgets was witnessed when compared to baseline models through comparative analysis. The results verify the framework's ability to provide low latency and correct DDoS mitigation directly on the IoT devices, which can be considered a feasible solution to achieve resilience improvement of critical IoT deployments in health care, industrial automation, and smart cities.
Selvi. T, Jayaganesh. J· International journal of com...· 0 citations
The rapid growth of Internet of Things (IoT) devices has significantly improved connectivity across smart environments. However, the resource-constrained nature of IoT devices and their limited built-in security mechanisms make them highly vulnerable to evolving cyberattacks. Traditional intrusion detection systems relying on signature-based or static rule sets are often ineffective against previously unseen attacks. This study proposes a hybrid machine learning-based intrusion detection and prevention framework for securing IoT networks. The framework integrates Isolation Forest, Autoencoder, Extreme Gradient Boosting, and Bidirectional Long Short-Term Memory models within a stacked ensemble architecture to improve attack detection while reducing false-positive predictions. The ensemble outputs are combined using a Logistic Regression meta-classifier to generate the final threat score. Experimental evaluation using the UNSW-NB15 dataset demonstrates that Extreme Gradient Boosting achieved the highest individual Receiver Operating Characteristic-Area Under the Curve score of 0.91, while the proposed framework further enhances detection robustness through ensemble learning and automated prevention. A Flask-based monitoring dashboard provides real-time visualization of detection results, blocked IP addresses, alerts, and system performance.
Ruthwik Palem, Likhith Reddy Peketi, Vanathi M et al.· Cureus Journal of Computer S...· 0 citations
The exponentially increasing number of IoT devices and their corresponding cloud infrastructures increases the attack surface․ Classic rule-based schemes and cryptographic solutions are not well adapted to dynamic‚ heterogeneous‚ distributed‚ and resource-constrained IoT-cloud infrastructures․ Artificial intelligence (AI) based techniques such as machine learning (ML)‚ deep learning (DL) and federated learning (FL)‚ considered as a new model for intrusion detection systems (IDS) to assess the threats in real time and respond to the threats effectively in the dynamic environment․ This paper thoroughly reviews the state-of-the-art AI-based IDS in a layer-wise manner which consists of IoT and cloud stacks․ It categorizes popular cyber-attacks associated with each layer (perception‚ network‚ transport‚ processing and application) and correlate the attacks to machine learning classifiers (SVM‚ KNN‚ Random Forest‚ CNN‚ RNN/LSTM‚ Autoencoder) at shallow and deep learning levels․ The research incorporates federated IDS‚ graph neural networks‚ transformer architecture and explainable artificial intelligence as models of machine learning and further discusses prominent research issues (data scarcity‚ adversarial robustness‚ latency‚ transferability) and the future direction of next-generation IoT-cloud security․
A. Anitha, A. R, Arpita Nath Boruah et al.· International journal of com...· 0 citations
Internet of Things(IoT)/edge intrusion-detection systems operate on distributed traffic and system-state data whose distributions vary across gateways, services, and attack conditions. We study a server-assisted federated setting in which a teacher reference is fitted from a permitted server-accessible training pool and explicitly distinguish this simulation assumption from fully decentralized deployment. The proposed framework evaluates progressive local training through boundary stabilization, confidence-weighted decision distillation, representation alignment, and validation-quality-aware aggregation. The evaluation uses a leakage-controlled protocol: server and client validation subsets are held out before federated training, update quality and early stopping use validation data only, and the final-test split is evaluated once. Results on NSL-KDD, CIC-IDS2017, Edge-IIoTset, and the ToN-IoT network dataset show competitive primary performance and stronger robustness in several severe label-skew settings. On the Telemetry of Things(ToN-IoT) with Dirichlet alpha = 0.1, the proposed method achieves 91.46 ± 5.54 F1, compared with 53.73 ± 49.00 for FedAvg and 53.77 ± 48.92 for FedProx. The results do not establish universal superiority or a universally optimal stage order: competing methods remain stronger in selected stable and attack-shift settings. The framework is therefore presented as a bounded, server-assisted robustness-oriented training strategy for heterogeneous IoT/edge intrusion detection.
Xudong Yang, Zikui Lin, Qiuyan Li et al.· Electronics· 0 citations