{"title":"Lightweight spatial attention pyramid network-based image forgery detection optimized for real-time edge TPU deployment","authors":"Baby Sree Gangarapu , Rama Muni Reddy Yanamala , Archana Pallakonda , Hindupur Raghavender Vardhan , Rayappa David Amar Raj","doi":"10.1016/j.compeleceng.2025.110645","DOIUrl":"10.1016/j.compeleceng.2025.110645","url":null,"abstract":"<div><div>The widespread accessibility of image editing software has made image forgery a considerable threat in journalism, legal contexts, and social media, requiring effective and precise detection techniques. The Authors propose a Spatial Attention Pyramid Network (SAPN) that integrates multi-scale residual feature extraction with an adaptive spatial attention mechanism to tackle the difficulties of identifying subtle and localized alterations. SAPN attains enhanced forgery detection performance and computational efficiency by utilizing hierarchical feature learning and selectively augmenting regions susceptible to manipulation. Extensive experiments conducted on four benchmark datasets illustrate the effectiveness and generalizability of SAPN. On the CASIA V1 dataset, SAPN attains an accuracy of 94% and an AUC of 0.99, outperforming 29 state-of-the-art models. An ablation study further supports the contributions of the pyramid feature extraction and spatial attention modules to the overall performance improvements. Moreover, a lightweight model architecture, containing merely 0.57 million parameters, enables efficient real-time deployment on Edge TPU devices, with an average inference latency of 1.17 s per image. These results proclaim SAPN as a scalable and robust framework for image forgery detection and localization in real-world applications.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"128 ","pages":"Article 110645"},"PeriodicalIF":4.9,"publicationDate":"2025-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144919966","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Tong Anh Tuan , Pham Sy Nguyen , Pham Ngoc Van , Nguyen Duc Hai , Pham Duy Trung , Nguyen Thi Kim Son , Hoang Viet Long
{"title":"A novel framework for cross-platform malware detection via AFSP and ADASYN-based balancing","authors":"Tong Anh Tuan , Pham Sy Nguyen , Pham Ngoc Van , Nguyen Duc Hai , Pham Duy Trung , Nguyen Thi Kim Son , Hoang Viet Long","doi":"10.1016/j.compeleceng.2025.110625","DOIUrl":"10.1016/j.compeleceng.2025.110625","url":null,"abstract":"<div><div>The rapid spread of malware and the growing complexity of attack methods demand accurate and scalable detection solutions, particularly in classification techniques in which both feature selection and model selection play a critical role. However, malware datasets are often high-dimensional and imbalanced, leading to biased models and suboptimal classification performance. This paper introduces CMF, a novel cross-platform malware detection framework that integrates Adaptive Feature Selection and Projection (AFSP) for dimensionality reduction, Adaptive Synthetic Sampling (ADASYN) for data balancing, and voting ensemble learning for classification. ADASYN consistently outperforms SMOTE by adaptively oversampling hard-to-learn boundary regions, improving minority class detection. Meanwhile, AFSP preserves feature structures while reducing dimensions, while PCA only retains maximal variance directions, making AFSP more effective for malware classification. Extensive experiments on four comprehensive available malware datasets demonstrate that CMF outperforms traditional and deep learning-based approaches, achieving superior accuracy and robustness. Notably, the highest improvement was close to 5% compared to the state-of-the-art on the CIC-MalMem-2022 (16 classes) dataset. CMF framework is highly effective detection of malware variants across multiple operating systems, for instance Windows, Linux, and Android, and heterogeneous cloud environments. This confirms CMF framework as a scalable and high-performance solution for real-world malware detection across environmental diversity.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"128 ","pages":"Article 110625"},"PeriodicalIF":4.9,"publicationDate":"2025-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144919970","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Range anxiety mitigation through blockchain-based mobile charging delivery service in Internet of Electric Vehicles","authors":"Brijmohan Lal Sahu, Preeti Chandrakar","doi":"10.1016/j.compeleceng.2025.110647","DOIUrl":"10.1016/j.compeleceng.2025.110647","url":null,"abstract":"<div><div>Sensor-rich Electric Vehicles (EVs) in Vehicular Ad-Hoc Networks (VANETs) have transformed it into the Internet of Electric Vehicles (IoEV). Identified challenges in climate-friendly and low-carbon footprint EVs are: First, range anxiety due to the unavailability of charging stations, battery charging duration and capacity in EV users. Second, the threat of privacy leakage and the limitations of software-based security in IoEV. Third is the absence of a mechanism to ensure the delivery of the promised battery and to verify delivery. The proposed framework focused on reducing range anxiety through the delivery of swappable EV batteries at locations as Mobile Charging Delivery Service (MCDS). The software and hardware-level security is provided by the integration of blockchain and Physical Unclonable Functions (PUFs). A Proof-of-Promised Battery (PoPB) mechanism is also introduced to ensure the delivery. Experimental results and Scyther tool analysis prove the effectiveness of the proposed framework and its superiority over recent works.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"128 ","pages":"Article 110647"},"PeriodicalIF":4.9,"publicationDate":"2025-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144919971","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Novel three-phase phase-locked loop design for microgrid inverter based on harmonic detection technology","authors":"Wansheng Jia , Xiaoxin Hou , Tianlei Zhang , Yongliang Hao , Ning Zhang","doi":"10.1016/j.compeleceng.2025.110642","DOIUrl":"10.1016/j.compeleceng.2025.110642","url":null,"abstract":"<div><div>As a key component in distributed generation systems, the inverter synchronization unit (Phase-Locked Loop, PLL) is critical for stable control system output. Under grid unbalanced conditions, the traditional Synchronous Reference Frame PLL(SRF-PLL) fails to lock phase accurately. Existing improved schemes integrating filters into PLLs suppress unbalanced interference but reduce bandwidth, degrade dynamic response (prolonging phase-locking time), and face challenging filter parameter tuning under diverse conditions. Additionally, frequency, as the derivative of phase angle, is significantly affected by phase changes. To address these issues, this paper introduces the Triple Fundamental Frequency concept for three-phase systems, proposing a novel orthogonal signal generation method and a corresponding Triple Fundamental Frequency PLL architecture, enabling stable frequency output. To further improve the performance of the phase - locked loop, a harmonic quantization method is integrated to quantify and offset harmonic impacts on the PLL by subtracting quantified data from dynamic outputs. Leveraging triple frequency advantages, this method markedly enhances system dynamic response. Simulation experiments verify the superiority of the proposed harmonic quantization triple fundamental frequency PLL in dynamic response.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"128 ","pages":"Article 110642"},"PeriodicalIF":4.9,"publicationDate":"2025-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144920326","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sijjad Ali , Shuaib Ahmed Wadho , Kazim Raza Talpur , Bandeh Ali Talpur , Khulud Salem Alshudukhi , Mamoona Humayun , Samar Raza Talpur , Mohd Abdullah Al Mamun , Muhammad Naseem , Adeel Abro , Dhani Bux Talpur , Asadullah Shah
{"title":"Next-Generation Quantum Security: The Impact of Quantum Computing on Cybersecurity—Threats, Mitigations, and Solutions","authors":"Sijjad Ali , Shuaib Ahmed Wadho , Kazim Raza Talpur , Bandeh Ali Talpur , Khulud Salem Alshudukhi , Mamoona Humayun , Samar Raza Talpur , Mohd Abdullah Al Mamun , Muhammad Naseem , Adeel Abro , Dhani Bux Talpur , Asadullah Shah","doi":"10.1016/j.compeleceng.2025.110649","DOIUrl":"10.1016/j.compeleceng.2025.110649","url":null,"abstract":"<div><div>The rapid advancement of quantum computing poses unprecedented threats to classical cryptographic systems, jeopardizing the security of digital infrastructures worldwide. This review paper comprehensively examines the transformative impact of quantum computing on cybersecurity, highlighting vulnerabilities introduced by algorithms like Shor’s and Grover’s, which can break widely used encryption methods such as RSA, ECC, and AES. It underscores the urgency of adopting quantum-resistant solutions, including post-quantum cryptography (PQC) and quantum key distribution (QKD), to mitigate these risks. The paper also explores emerging hybrid systems, quantum-safe blockchain, and IoT security, offering actionable insights for transitioning to quantum-resilient frameworks. By synthesizing interdisciplinary research, this work emphasizes the need for global collaboration, standardization, and innovation to safeguard data integrity and privacy in the impending quantum era, making it a pivotal resource for researchers, practitioners, and policymakers.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"128 ","pages":"Article 110649"},"PeriodicalIF":4.9,"publicationDate":"2025-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144922413","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jai Prakash Kushwaha , Saumya Bhadauria , Shashikala Tapaswi
{"title":"Unveiling IoT ecosystem security: A review of intelligent IDS, trends, challenges, and future directions","authors":"Jai Prakash Kushwaha , Saumya Bhadauria , Shashikala Tapaswi","doi":"10.1016/j.compeleceng.2025.110626","DOIUrl":"10.1016/j.compeleceng.2025.110626","url":null,"abstract":"<div><div>The rapid increase in the use of Internet of Things (IoT) devices has transformed everyday life and industries such as healthcare, transportation, and smart homes. However, these devices, often limited in resources, depend on communication across edge, fog, and cloud layers, creating vulnerabilities that attackers can exploit. This paper provides a comprehensive review of intelligent intrusion detection system (IDS) tailored for IoT security, focusing on solutions that utilize Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL). We analyze existing IDS approaches for IoT devices and secure communication across the edge, fog, and cloud layers, highlighting their strengths and limitations. Additionally, we identify Key research challenges include computational complexity, real-time adaptability, and energy efficiency in Edge Computing. To address these gaps, we propose future research directions, including neuromorphic computing for ultra-fast IDS, self-evolving AI-driven IDS, hyper-personalized anomaly detection, federated learning for privacy- preserving security, and explainable AI (XAI) for human–AI collaboration. By integrating these innovations, we envision next-generation IDS solutions that offer scalable, interpretable, and energy- efficient security frameworks for the dynamic IoT ecosystem.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"128 ","pages":"Article 110626"},"PeriodicalIF":4.9,"publicationDate":"2025-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144919972","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ebtasam Ahmad Siddiqui , Vijayshri Chaurasia , Madhu Shandilya , Jai Kumar Chaurasia
{"title":"Classification of lung cancer computed tomography scans using deep networks: A review","authors":"Ebtasam Ahmad Siddiqui , Vijayshri Chaurasia , Madhu Shandilya , Jai Kumar Chaurasia","doi":"10.1016/j.compeleceng.2025.110641","DOIUrl":"10.1016/j.compeleceng.2025.110641","url":null,"abstract":"<div><div>Lung cancer continues to be the leading cause of cancer-related deaths worldwide, with its mortality rate steadily increasing. Early detection is crucial for improving survival rates, yet the overwhelming workload on radiologists and the shortage of specialists make accurate and timely diagnosis challenging. The large volume of medical images from CT scans, MRIs, and X-rays further complicates the diagnostic process, increasing the likelihood of errors or delays. To address this issue, researchers have focused on developing automated systems that assist in lung cancer detection and classification. This study explores various techniques, including computer-aided detection (CADe) and computer-aided diagnosis (CADx) systems, which utilize medical imaging to identify lung nodules and classify them as benign or malignant. A key objective of this research is evaluating different classifiers to determine the most effective model for accurate classification. Among the models studied, Convolutional Neural Networks (CNNs) have shown the best performance in distinguishing malignant from benign tumors due to their ability to extract complex patterns from medical images. Advanced CNN architectures such as ResNet, VGGNet, and EfficientNet outperform traditional classifiers in terms of accuracy and efficiency. The study also examines segmentation techniques, feature extraction methods, and classification challenges, proposing hybrid AI models and improved data augmentation strategies to enhance diagnostic precision. By addressing these critical aspects, this research aims to develop a robust and automated lung cancer diagnostic framework that enhances early detection, supports radiologists, and improves patient outcomes.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"128 ","pages":"Article 110641"},"PeriodicalIF":4.9,"publicationDate":"2025-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144917911","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"PUF enabled and dynamic anonymous certificateless batch-verifiable signcryption for IoMT","authors":"Girraj Kumar Verma , Asheesh Tiwari , Manoj Wadhwa , Neeraj Kumar","doi":"10.1016/j.compeleceng.2025.110623","DOIUrl":"10.1016/j.compeleceng.2025.110623","url":null,"abstract":"<div><div>The convergence of the Internet of Things (IoT) and e-Healthcare has given rise to the Internet of Medical Things (IoMT). In IoMT environments, sensor nodes deployed on a patient’s body collect vital health statistics (e.g., pulse rate, blood sugar level, etc.) and transmit them to a medical server (MS), which subsequently shares the data with medical professionals for diagnosis and treatment. However, the wireless communication channels used in such systems are inherently vulnerable to various security threats. To address this, recently, Singh <em>et al</em>. proposed a certificateless aggregate signcryption (CLASC) scheme to protect sensitive patient physiological data. However, the present study reveals a critical vulnerability in their design—specifically, a compromised MS can successfully forge signatures on behalf of sensor nodes without possessing their secret keys. To address this flaw, we propose a security-enhanced Dynamic Anonymous Aggregate Signcryption (DAASC) scheme. The design employs Physically Unclonable Functions (PUFs) to protect the key generation center’s master secret key from physical capture attacks, while a fuzzy extractor ensures dynamic anonymity. The proposed scheme is rigorously analyzed through both formal and informal security analysis to demonstrate resilience against various practical attacks. Furthermore, a comprehensive performance evaluation confirms that the devised DAASC scheme is efficient in terms of computational overhead and bandwidth utilization, making it well-suited for secure and lightweight deployment in IoMT environments.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"128 ","pages":"Article 110623"},"PeriodicalIF":4.9,"publicationDate":"2025-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144912000","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Novel full fractional-order control and Lyapunov stability approach using genetic algorithm optimization for high-performance wind turbines","authors":"Yassamine Zoubaa, Sihame Chouiekh, Ayoub EL Bakri, Selma Sefriti, Ismail Boumhidi","doi":"10.1016/j.compeleceng.2025.110658","DOIUrl":"10.1016/j.compeleceng.2025.110658","url":null,"abstract":"<div><div>Wind energy systems play a key role in the global shift toward renewable energy. However, effectively controlling variable-speed wind turbines (VSWTs) under fluctuating wind conditions remains challenging. This paper presents a nonlinear fractional-order control method designed for VSWTs, using a fractional-order two-mass model that captures flexible shaft dynamics at low speeds. A novel control strategy based on full fractional-order sliding mode control (FFOSMC) and full fractional-order integral sliding mode control (FFOISMC) is introduced to enhance system stability, accuracy, and robustness. The fractional-order design leverages memory and non-local effects for improved performance. To tune control parameters, an evolutionary optimization technique is applied, ensuring adaptability across operating conditions. Stability is analyzed using the fractional-order Lyapunov method. Simulation results show that the proposed method outperforms conventional approaches in tracking accuracy, torque response, and energy efficiency. This work contributes to advanced wind turbine control and supports the development of smart renewable energy systems.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"128 ","pages":"Article 110658"},"PeriodicalIF":4.9,"publicationDate":"2025-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144917910","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Enhanced energy management and cyber-resilience of integrated energy systems based on optimal energy storage system and demand response: A deep reinforcement learning approach","authors":"Alireza Moridi , Reza Sharifi , Hasan Doagou-Mojarrad , Javad Olamaei","doi":"10.1016/j.compeleceng.2025.110657","DOIUrl":"10.1016/j.compeleceng.2025.110657","url":null,"abstract":"<div><div>The integrated multi-carrier energy system (IMCES) optimal operation based on dynamic variables is complex and challenging. This study proposes a framework for multi-level energy management in the IMCES structure. The framework takes into account demand response (DR) programs, effective participation of energy storage systems, and presents the cyberspace structure's resilience against cyber-attacks such as false data injection (FDI). The framework improves the resilience by using a robust multi-agent deep reinforcement learning (RMADRL) strategy. The multi-objective function has been formulated in three levels. The first-level objectives are to optimize the operation of IMCES through the DR program and to optimize the participation of ESS units through the wholesale and retail market prices. The second-level objectives aim to minimize the cost of greenhouse gas emissions, while the third-level objectives evaluate the cyberspace based on fixed and random cyber attacks. The RMADRL strategy is a method that uses the Markov decision process equations to evaluate optimal actions and policies. The multi-agent soft actor-critic method is utilized for this purpose. By executing the DR program, the total operation cost can be reduced by 9.9%. Furthermore, executing the DR program and incorporating the ESSs effective participation can further reduce the total operation cost by 15.79%.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"128 ","pages":"Article 110657"},"PeriodicalIF":4.9,"publicationDate":"2025-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144911999","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}