The increasing prevalence of adversarial evasion techniques poses a significant challenge to the reliability of intrusion detection systems (IDSs) in Internet-of-Things (IoT) environments. Minor manipulations of traffic telemetry can alter temporal behaviour or frequency-level patterns, leading to degraded detection performance and potential security failures. This study presents the Multi-Frequency Temporal Spatio-Transformer (MFTST), a computational framework designed to improve adversarial robustness in IoT intrusion detection. MFTST combines temporal Transformer-based encoding with multi-frequency channel attention to capture both sequential traffic behaviour and frequency-level variations in learned traffic representations. The framework is evaluated using a Composite attack that emulates the detection-side effects of two representative defense-evasion behaviours: obfuscation (T1027) and indicator tampering (T1070), as commonly described in the MITRE ATT&CK knowledge base. The Composite attack jointly perturbs temporal attention behaviour and frequency-domain traffic representations to assess the resilience of MFTST against timing-based masking, attention disruption, and frequency-domain perturbations. To improve robustness, the model is trained using a composite adversarial optimization strategy that jointly considers classification performance, temporal-attention stability, and frequency-domain perturbation control. Experimental evaluations on MQTTset and X-IIoTID demonstrate that MFTST improves detection performance under both clean and adversarial conditions. The results show that adversarial training improves multiclass accuracy from 0.8314 to 0.8558 on MQTTset and from 0.8758 to 0.9192 on X-IIoTID. Under stronger adversarial evaluation, MFTST also maintains higher robustness than conventional machine-learning, deep-learning, and robustness-oriented baselines. These findings indicate that temporally conditioned frequency attention can improve both detection reliability and interpretability in adversarial IoT security monitoring.

The rapid expansion of IoT networks has increased the risk of cyber threats, making intrusion detection systems (IDS) critical for maintaining security. However, most of the existing IDS rely on computationally intensive deep learning architectures, rendering them unsuitable for IoT environments with limited resources. Additionally, existing IDS approaches, including those using Knowledge Distillation (KD), often fail to capture the complex temporal dependencies and contextual relationships inherent in IoT traffic, which limits their ability to detect complex multi-stage attacks. Furthermore, these models frequently lack transparency, hindering effective decision-making by security experts. To address these gaps, we propose DistillGuard, a novel IDS framework designed specifically for IoT networks. The proposed framework employs a Transformer-based teacher model, which utilizes a hybrid attention mechanism combining multi-head self-attention (MHSA) and cross-attention layers to effectively capture both temporal and contextual patterns in network traffic. The framework further incorporates a Selective Gradient-Based Knowledge Distillation (SG-KD) process to transfer critical knowledge from the teacher model to a lightweight student model, optimizing performance while reducing computational costs. In addition,’DistillGuard’ integrates gradient contribution heatmaps, layer-wise contribution, and gradient selection impact analysis to provide detailed explanability, enabling security experts to understand which layers contribute to the detection of attacks. Experimental results demonstrate that’DistillGuard’ achieves superior detection accuracy and efficiency compared to existing state-of-the-art IDS models.

The increasing adoption of Industrial Internet of Things (IIoT) networks has introduced new security challenges, particularly to ensure software security against evolving malware threats. IIoT systems rely on interconnected edge, cloud, and embedded devices, which are highly vulnerable to malware attacks that exploit software vulnerabilities, propagate across networks, and compromise industrial operations. However, existing malware detection approaches often struggle with resource constraints, high-dimensional feature spaces, and the need for real-time adaptability, making them inefficient for large-scale IIoT deployments. To address these challenges, this paper presents "GWPSO-GAMD," a resource-efficient malware detection framework designed to enhance software security in IIoT networks. The framework integrates a hybrid metaheuristic feature selection algorithm—Grey Wolf Optimization and Particle Swarm Optimization (GWPSO)—to identify the most discriminative and computationally efficient features, reducing processing overhead while maintaining high detection accuracy. These features are then analyzed by the Graph Android Malware Detector (GAMD), which leverages graph convolutional networks (GCNs) and attention mechanisms to model malware propagation behaviors and uncover complex attack patterns in IIoT environments. Empirical evaluations on two open-source malware datasets, CIC-MalDroid-2020 and CIC-MalMem-2022, demonstrate that the proposed model achieves detection accuracy above 98.41% while significantly reducing CPU usage by 47%, memory footprint by 57%, and training time by 67%. The results highlight GWPSO-GAMD’s ability to provide scalable, real-time malware detection for resource-constrained IIoT systems, advancing the vision of secure, intelligent, and resource-aware IIoT networks.

The Industrial Internet of Things (IIoT) is a collection of interconnected smart sensors and actuators with industrial software tools and applications. IIoT aims to enhance manufacturing and industrial processes by capturing and analyzing real-time industrial data. However, the heterogeneous and homogeneous nature of IIoT networks makes them vulnerable to several security threats. As data is transmitted over an insecure communication medium, intruders may intercept communication among different entities and perform malicious activities. Consequently, ensuring the security and privacy of data transmitted in IIoT networks is essential. Motivated by the aforementioned challenges, this article presents a deep-learning-integrated blockchain framework for securing IIoT networks. Specifically, first, we design a private blockchain-based secure communication among the IIoT entities using session-based mutual authentication and key agreement mechanism. In this approach, the Proof-of-Authority (PoA) consensus mechanism is used for verification of the transactions and block creation based on the voting of miners over the cloud server. Second, we design a novel deep-learning-based intrusion detection system that combines contractive sparse autoencoder (CSAE), attention-based bidirectional long short-term memory (ABiLSTM) networks, and softmax classifier for cyberattack detection. The practical implementation of blockchain and deep-learning techniques proves the effectiveness of the proposed framework.

The Internet of Medical Things (IoMT) has revolutionized healthcare, but its vulnerabilities demand robust security solutions, especially for resource-constrained devices. In this research, we introduce an innovative Software as a Service (SaaS)-based Intrusion Detection System (IDS) designed specifically for the unique challenges of IoMT, deploying at the edge for enhanced efficiency. Our proposed IDS incorporates a multi-faceted approach: Firstly, it leverages the Particle Swarm Optimization (PSO) algorithm for feature engineering, optimizing data representation to reduce computational overhead on resource-constrained devices. Secondly, a diverse ensemble of machine learning and deep learning models is employed to detect a wide array of intrusion attempts within IoMT networks. Thirdly, interpretation is achieved using SHapley Additive exPlanations (SHAP), providing transparency and understanding of the decision-making process. By combining intelligence, efficiency, explainability, and deploying as a SaaS solution at the network edge, our IDS not only bolsters the security of resource-constrained IoMT devices but also empowers healthcare professionals with actionable insights, ensuring patient data privacy and network integrity in this dynamic and critical domain. Finally, the results using a publicly available healthcare dataset namely WUSTL-EHMS-2020 proves the effectiveness of the proposed IDS over some recent state-of-the-art works.

Abstract An automated computer‐assisted medical diagnosis that combines latest medical approaches and the advanced machine learning algorithms is a very crucial multidisciplinary technology, generating correct and noninvasive diagnoses of multiple diseases like breast cancer. The work proposed in this article focuses on the development of a biomedical computer‐assisted diagnosis model that can classify digital mammography as normal (healthy) or abnormal, and further, as malignant or benign. The proposed approach employs the discrete Chebyshev transform to extract the features. Then, the kernel principal component analysis technique is used to extract the discriminating features from the original feature vector. Subsequently, an optimized kernel extreme learning machine is proposed as a classifier to detect the tumors present in the mammographic images. Because the efficiency of the proposed classifier depends on its characteristic kernel variable, the main idea of the present work is to choose the most appropriate features from the downsized feature set and simultaneously obtain the optimized value of the aforementioned parameter. To validate the efficiency of the proposed work, the proposed scheme is performed on two publicly available data sets, namely the Mammographic Image Analysis Society data set and the INbreast data set. From the experimental analysis and its results, it is showed that for both normal–abnormal and malignant–benign classification, the proposed approach results in accuracy of 100% for the first data set. However, in the case of malignant–benign classification, the proposed approach gives an accuracy of 99.93% for the second data set. Further, it is also observed that the proposed approach exhibits highest performance as compared to that of the other approaches. Additionally, the ANOVA test is evaluated to demonstrate that the achievement of the proposed approach is significantly good than that of the other existing approaches.