Computers & Electrical Engineering最新文献_第7页

A multi-stage framework for scalable and context-aware intrusion detection in IoT-cloud systems using deep latent modeling and graph-based attack classification 使用深度潜在建模和基于图的攻击分类，用于物联网云系统中可扩展和上下文感知入侵检测的多阶段框架

IF 4.9 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2026-01-10 DOI: 10.1016/j.compeleceng.2026.110949

Rajakumar Ponnumani , Nisha Vasudeva , Thenmozhi Elumalai , Prabu Kaliyaperumal , Balamurugan Balusamy , Francesco Benedetto

The rapid proliferation of Internet of Things (IoT) devices in cloud environments has led to an expanded attack surface and increased susceptibility to diverse and evolving cyber threats. This study proposes a robust, multi-stage hybrid intrusion detection framework designed to address the challenges of high-dimensional data, class imbalance, and dynamic traffic in IoT ecosystems. The framework integrates Variational AutoEncoder (VAE) for latent feature compression, Isolation Forest (IF) for unsupervised anomaly detection, and Graph Attention Network (GAT) for relational modeling and multi-class classification. The CIC IoT-DIAD 2024 dataset is utilized to evaluate performance across multiple attack categories. The VAE extracts compact latent representations, enabling effective anomaly detection through IF. Detected anomalies are then structured into graph topologies, and classified by GAT based on node-level features and inter-node relations. Experimental results demonstrate superior detection performance with an overall accuracy of 99.08% and an F1-score of 98.03%, outperforming traditional and deep learning baselines. The proposed system exhibits strong scalability, generalization, and adaptability to dynamic IoT-cloud threat landscapes. Furthermore, its graph-based reasoning enhances interpretability and supports actionable insights for real-time threat response. Overall, this framework establishes a practical pathway toward intelligent, adaptive, and interpretable intrusion diagnosis in next-generation IoT-cloud ecosystems.

物联网（IoT）设备在云环境中的快速扩散导致了攻击面的扩大，并增加了对各种不断发展的网络威胁的敏感性。本研究提出了一种鲁棒的多阶段混合入侵检测框架，旨在解决物联网生态系统中高维数据、类别不平衡和动态流量的挑战。该框架集成了用于潜在特征压缩的变分自编码器（VAE）、用于无监督异常检测的隔离森林（IF）和用于关系建模和多类分类的图注意网络（GAT）。CIC IoT-DIAD 2024数据集用于评估多个攻击类别的性能。VAE提取紧凑的潜在表示，通过中频实现有效的异常检测。然后将检测到的异常结构成图拓扑，并根据节点级特征和节点间关系使用GAT进行分类。实验结果表明，该方法具有优异的检测性能，总体准确率为99.08%，f1分数为98.03%，优于传统和深度学习基线。该系统具有很强的可扩展性、通用性和对动态物联网云威胁环境的适应性。此外，其基于图的推理增强了可解释性，并支持实时威胁响应的可操作见解。总体而言，该框架为下一代物联网云生态系统中的智能、自适应和可解释入侵诊断建立了一条实用途径。

{"title":"A multi-stage framework for scalable and context-aware intrusion detection in IoT-cloud systems using deep latent modeling and graph-based attack classification","authors":"Rajakumar Ponnumani , Nisha Vasudeva , Thenmozhi Elumalai , Prabu Kaliyaperumal , Balamurugan Balusamy , Francesco Benedetto","doi":"10.1016/j.compeleceng.2026.110949","DOIUrl":"10.1016/j.compeleceng.2026.110949","url":null,"abstract":"<div><div>The rapid proliferation of Internet of Things (IoT) devices in cloud environments has led to an expanded attack surface and increased susceptibility to diverse and evolving cyber threats. This study proposes a robust, multi-stage hybrid intrusion detection framework designed to address the challenges of high-dimensional data, class imbalance, and dynamic traffic in IoT ecosystems. The framework integrates Variational AutoEncoder (VAE) for latent feature compression, Isolation Forest (IF) for unsupervised anomaly detection, and Graph Attention Network (GAT) for relational modeling and multi-class classification. The CIC IoT-DIAD 2024 dataset is utilized to evaluate performance across multiple attack categories. The VAE extracts compact latent representations, enabling effective anomaly detection through IF. Detected anomalies are then structured into graph topologies, and classified by GAT based on node-level features and inter-node relations. Experimental results demonstrate superior detection performance with an overall accuracy of 99.08% and an F1-score of 98.03%, outperforming traditional and deep learning baselines. The proposed system exhibits strong scalability, generalization, and adaptability to dynamic IoT-cloud threat landscapes. Furthermore, its graph-based reasoning enhances interpretability and supports actionable insights for real-time threat response. Overall, this framework establishes a practical pathway toward intelligent, adaptive, and interpretable intrusion diagnosis in next-generation IoT-cloud ecosystems.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"131 ","pages":"Article 110949"},"PeriodicalIF":4.9,"publicationDate":"2026-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145927454","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}

引用次数: 0

Cryptanalysis of an image encryption algorithm using Latin squares 一种使用拉丁平方的图像加密算法的密码分析

IF 4.9 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2026-01-09 DOI: 10.1016/j.compeleceng.2026.110950

Rong Zhou

This study conducts cryptanalysis on a Novel Image Cryptosystem based on Latin Squares (NIC-LS). The NIC-LS adopts a multi-round encryption structure, with row or column scrambling alternating with diffusion. It leverages properties of Latin squares generated by the Coupled Map Lattice (CML) system to determine scrambling/diffusion selection modes, aiming for enhanced encryption performance. However, all diffusion operations in NIC-LS rely solely on simple modular addition—this flaw gives rise to an equivalent algorithm for the cryptosystem. When a Differential Attack (DA) is applied to this equivalent scheme, the system degenerates into a linear one: all diffusion effects are eliminated, leaving only the scrambling component. Building on the superposition principle and standard orthogonal basis concept, this study further breaks the equivalent algorithm (and thus NIC-LS) via a Chosen-Ciphertext Attack (CCA). Notably, the attack’s computational complexity is extremely low and some countermeasures are discussed based on the cryptanalysis. Both theoretical analysis and experimental results confirm the proposed cryptanalysis is effective and practically feasible.

本文对一种基于拉丁平方（NIC-LS）的新型图像密码系统进行了密码分析。NIC-LS采用多轮加密结构，行或列置乱与扩散交替进行。它利用耦合映射格（CML）系统生成的拉丁平方的特性来确定置乱/扩散选择模式，旨在提高加密性能。然而，NIC-LS中的所有扩散操作仅依赖于简单的模加法，这一缺陷导致了密码系统的等效算法。当微分攻击（DA）应用于该等效方案时，系统退化为线性系统，消除了所有扩散效应，只留下置乱分量。在叠加原理和标准正交基概念的基础上，本研究通过选择密文攻击（CCA）进一步打破等效算法（从而打破NIC-LS）。值得注意的是，该攻击的计算复杂度极低，并讨论了基于密码分析的对策。理论分析和实验结果均证实了该算法的有效性和实际可行性。

{"title":"Cryptanalysis of an image encryption algorithm using Latin squares","authors":"Rong Zhou","doi":"10.1016/j.compeleceng.2026.110950","DOIUrl":"10.1016/j.compeleceng.2026.110950","url":null,"abstract":"<div><div>This study conducts cryptanalysis on a Novel Image Cryptosystem based on Latin Squares (NIC-LS). The NIC-LS adopts a multi-round encryption structure, with row or column scrambling alternating with diffusion. It leverages properties of Latin squares generated by the Coupled Map Lattice (CML) system to determine scrambling/diffusion selection modes, aiming for enhanced encryption performance. However, all diffusion operations in NIC-LS rely solely on simple modular addition—this flaw gives rise to an equivalent algorithm for the cryptosystem. When a Differential Attack (DA) is applied to this equivalent scheme, the system degenerates into a linear one: all diffusion effects are eliminated, leaving only the scrambling component. Building on the superposition principle and standard orthogonal basis concept, this study further breaks the equivalent algorithm (and thus NIC-LS) via a Chosen-Ciphertext Attack (CCA). Notably, the attack’s computational complexity is extremely low and some countermeasures are discussed based on the cryptanalysis. Both theoretical analysis and experimental results confirm the proposed cryptanalysis is effective and practically feasible.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"131 ","pages":"Article 110950"},"PeriodicalIF":4.9,"publicationDate":"2026-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145927514","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}

引用次数: 0

Empowering SAARC's energy future: A PESTEL-SWOT roadmap for super smart grids and P2P energy trading 助力南盟的能源未来：超级智能电网和P2P能源交易的PESTEL-SWOT路线图

IF 4.9 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2026-01-09 DOI: 10.1016/j.compeleceng.2025.110932

Marriam Liaqat , Ali Raza , Muhammad Sajid Iqbal , Muhammad Adnan , Usman Abbasi , Maqsood Khan

The super smart grid (SSG) is a revolutionary grid which offers significant fossil fuel elimination, emissions reduction, renewable energy integration, and demand fulfillment. However, such mega grids are in the strategic analysis stage due to the involvement of multiple countries and complexities. Although the existing literature has performed different types of analysis for the different SSGs around the world, there is a lack of studies on the strategic analysis of the SSG planned by the South Asian Association for Regional Cooperation (SAARC). For the first time, this review paper presents the hybrid PESTEL-SWOT analysis for the futuristic SAARC SSG. This paper offers important insights and strategies for the implementation of the futuristic SAARC SSG. For instance, a practical strategy towards the emergence of the SAARC SSG is the encouragement of the P2P trading at a very basic level through the hierarchical integration of thousands of prosumers, prosumer communities, and national grids.

超级智能电网（SSG）是一种革命性的电网，它提供了显著的化石燃料消除、减排、可再生能源整合和需求满足。然而，由于多个国家的参与和复杂性，这类巨型电网还处于战略分析阶段。虽然已有文献对世界各地不同的可持续发展战略进行了不同类型的分析，但对南亚区域合作联盟（SAARC）规划的可持续发展战略进行战略分析的研究较少。本文首次采用PESTEL-SWOT混合分析方法对未来南亚区域合作联盟（SAARC） SSG进行分析。本文为未来南盟战略合作集团的实施提供了重要的见解和策略。例如，南盟SSG出现的一个实用策略是通过成千上万的产消者、产消者社区和国家电网的分层整合，在非常基本的层面上鼓励P2P交易。

{"title":"Empowering SAARC's energy future: A PESTEL-SWOT roadmap for super smart grids and P2P energy trading","authors":"Marriam Liaqat , Ali Raza , Muhammad Sajid Iqbal , Muhammad Adnan , Usman Abbasi , Maqsood Khan","doi":"10.1016/j.compeleceng.2025.110932","DOIUrl":"10.1016/j.compeleceng.2025.110932","url":null,"abstract":"<div><div>The super smart grid (SSG) is a revolutionary grid which offers significant fossil fuel elimination, emissions reduction, renewable energy integration, and demand fulfillment. However, such mega grids are in the strategic analysis stage due to the involvement of multiple countries and complexities. Although the existing literature has performed different types of analysis for the different SSGs around the world, there is a lack of studies on the strategic analysis of the SSG planned by the South Asian Association for Regional Cooperation (SAARC). For the first time, this review paper presents the hybrid PESTEL-SWOT analysis for the futuristic SAARC SSG. This paper offers important insights and strategies for the implementation of the futuristic SAARC SSG. For instance, a practical strategy towards the emergence of the SAARC SSG is the encouragement of the P2P trading at a very basic level through the hierarchical integration of thousands of prosumers, prosumer communities, and national grids.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"131 ","pages":"Article 110932"},"PeriodicalIF":4.9,"publicationDate":"2026-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145927455","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}

引用次数: 0

Cyber risk quantification for adversarial machine learning attacks 对抗性机器学习攻击的网络风险量化

IF 4.9 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2026-01-09 DOI: 10.1016/j.compeleceng.2026.110964

Jasmita Malik, Raja Muthalagu, Pranav M. Pawar, Mithun Mukherjee

Adversarial machine learning (AML) attacks including evasion, poisoning, and privacy-targeting techniques represent a new class of evolving threats to AI systems. However, traditional cyber risk quantification approaches struggle to capture the uncertainty and impact of such dynamic threats. This study introduces a novel framework to quantify cyber risk exposure and business impact stemming from new-age AML attacks. Leveraging Monte Carlo simulations, the framework models probabilistic loss distributions based on attack likelihoods and impact ranges. Applied to a ransomware attack scenario on a machine learning system, the framework estimates an Annualized Loss Expectancy of approximately $1.6 million to an organization, revealing the potential for unexpected heavy-tail, high-cost outcomes. The framework is further validated across diverse adversarial scenarios, including evasion, poisoning, and privacy attacks. The results provide decision-makers with a structured way to assess control effectiveness and prioritize cybersecurity investments using quantitative metrics. This work bridges the gap between technical threat intelligence and strategic cybersecurity investment financial planning, offering a practical path toward resilient and secure deployment of AI systems in organizations.

对抗性机器学习（AML）攻击，包括逃避、中毒和隐私定位技术，代表了人工智能系统面临的一类不断发展的新威胁。然而，传统的网络风险量化方法难以捕捉这种动态威胁的不确定性和影响。本研究引入了一个新的框架来量化新时代“反洗钱”攻击所带来的网络风险暴露和业务影响。利用蒙特卡罗模拟，该框架基于攻击可能性和影响范围对概率损失分布进行建模。应用于机器学习系统上的勒索软件攻击场景，该框架估计一个组织的年预期损失约为160万美元，揭示了意想不到的重尾、高成本结果的可能性。该框架在不同的对抗性场景中得到进一步验证，包括逃避、中毒和隐私攻击。研究结果为决策者提供了一种结构化的方法来评估控制效果，并使用定量指标确定网络安全投资的优先级。这项工作弥合了技术威胁情报和战略网络安全投资财务规划之间的差距，为组织中弹性和安全部署人工智能系统提供了切实可行的途径。

{"title":"Cyber risk quantification for adversarial machine learning attacks","authors":"Jasmita Malik, Raja Muthalagu, Pranav M. Pawar, Mithun Mukherjee","doi":"10.1016/j.compeleceng.2026.110964","DOIUrl":"10.1016/j.compeleceng.2026.110964","url":null,"abstract":"<div><div>Adversarial machine learning (AML) attacks including evasion, poisoning, and privacy-targeting techniques represent a new class of evolving threats to AI systems. However, traditional cyber risk quantification approaches struggle to capture the uncertainty and impact of such dynamic threats. This study introduces a novel framework to quantify cyber risk exposure and business impact stemming from new-age AML attacks. Leveraging Monte Carlo simulations, the framework models probabilistic loss distributions based on attack likelihoods and impact ranges. Applied to a ransomware attack scenario on a machine learning system, the framework estimates an Annualized Loss Expectancy of approximately $1.6 million to an organization, revealing the potential for unexpected heavy-tail, high-cost outcomes. The framework is further validated across diverse adversarial scenarios, including evasion, poisoning, and privacy attacks. The results provide decision-makers with a structured way to assess control effectiveness and prioritize cybersecurity investments using quantitative metrics. This work bridges the gap between technical threat intelligence and strategic cybersecurity investment financial planning, offering a practical path toward resilient and secure deployment of AI systems in organizations.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"131 ","pages":"Article 110964"},"PeriodicalIF":4.9,"publicationDate":"2026-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145927515","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}

引用次数: 0

CleVer: A compute-and-leave anonymous verification framework for general purpose computation 聪明：一个用于通用计算的计算离开匿名验证框架

IF 4.9 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2026-01-09 DOI: 10.1016/j.compeleceng.2025.110931

Qiyuan Gao, Qianhong Wu, Qi Liu, Junxiang Nong

Verifiable computation is essential for ensuring correctness in decentralized systems, yet existing approaches rely heavily on circuit-based proofs, task decomposition, or trusted hardware, which introduce high overhead and limit generality. To address these challenges, we propose CleVer, a compute-and-leave anonymous verification framework for general-purpose computation.

CleVer avoids circuit-based proof generation by using snapshot-based state transitions, enabling single-step dispute resolution without task decomposition. We design a cumulative staking incentive mechanism that guarantees profitability for honest verifiers and enforces bounded finality under adversarial budgets. Furthermore, we introduce an anonymous verifier protocol to prevent targeted attacks and collusion. Security is analyzed under a formal threat model, and experiments demonstrate that CleVer significantly reduces verification rounds and on-chain burden compared with existing optimistic-verification frameworks. Our results show that CleVer provides an efficient, incentive-aligned, and privacy-preserving foundation for scalable off-chain computation.

可验证计算对于确保去中心化系统的正确性至关重要，但现有的方法严重依赖于基于电路的证明、任务分解或可信硬件，这些方法带来了高昂的开销并限制了通用性。为了解决这些挑战，我们提出了CleVer，这是一个用于通用计算的“计算离开”匿名验证框架。CleVer通过使用基于快照的状态转换来避免基于电路的证明生成，从而实现无需任务分解的单步争议解决。我们设计了一个累积的赌注激励机制，保证诚实的验证者的盈利能力，并在对抗预算下强制执行有限的最终性。此外，我们还引入了匿名验证者协议，以防止针对性攻击和共谋。在正式的威胁模型下分析了安全性，实验表明，与现有的乐观验证框架相比，CleVer显著减少了验证轮数和链上负担。我们的研究结果表明，CleVer为可扩展的链下计算提供了一个高效、激励一致、保护隐私的基础。

{"title":"CleVer: A compute-and-leave anonymous verification framework for general purpose computation","authors":"Qiyuan Gao, Qianhong Wu, Qi Liu, Junxiang Nong","doi":"10.1016/j.compeleceng.2025.110931","DOIUrl":"10.1016/j.compeleceng.2025.110931","url":null,"abstract":"<div><div>Verifiable computation is essential for ensuring correctness in decentralized systems, yet existing approaches rely heavily on circuit-based proofs, task decomposition, or trusted hardware, which introduce high overhead and limit generality. To address these challenges, we propose CleVer, a compute-and-leave anonymous verification framework for general-purpose computation.</div><div>CleVer avoids circuit-based proof generation by using snapshot-based state transitions, enabling single-step dispute resolution without task decomposition. We design a cumulative staking incentive mechanism that guarantees profitability for honest verifiers and enforces bounded finality under adversarial budgets. Furthermore, we introduce an anonymous verifier protocol to prevent targeted attacks and collusion. Security is analyzed under a formal threat model, and experiments demonstrate that CleVer significantly reduces verification rounds and on-chain burden compared with existing optimistic-verification frameworks. Our results show that CleVer provides an efficient, incentive-aligned, and privacy-preserving foundation for scalable off-chain computation.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"131 ","pages":"Article 110931"},"PeriodicalIF":4.9,"publicationDate":"2026-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145927513","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}

引用次数: 0

Fuzzy-enhanced variable weight graph convolutional networks for recommender systems 推荐系统的模糊增强变权图卷积网络

IF 4.9 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2026-01-08 DOI: 10.1016/j.compeleceng.2026.110970

Wanna Cui, Hak-Keung Lam

Recommender systems play an essential role in alleviating information overload by delivering personalized suggestions to users across domains such as e-commerce, restaurant services, and digital media. In recent years, graph-based approaches, particularly those leveraging graph convolutional networks (GCNs), have shown strong performance by modeling high-order connectivity. However, their effectiveness remains constrained by three critical challenges: the sparsity of user–item interactions, the presence of noisy or transient behaviors that distort preference modeling, and the underutilization of contextual information contained in reviews and product descriptions. To address these limitations, we propose a novel framework, termed fuzzy and variable weight graph convolutional network (FVW-GCN). The framework incorporates a fuzzy relation modeling module that enriches the adjacency structure by applying fuzzy C-means clustering to semantic embeddings extracted from pre-trained language models, thereby improving connectivity for sparse and long-tail items. In addition, a variable-weight GCN module is introduced, where a tuning GCN learns localized weight matrices from sampled subgraphs, which are then used by a tuned GCN to adaptively refine embeddings and suppress noisy signals. Through this combination, FVW-GCN effectively strengthens meaningful relations while reducing the influence of unreliable interactions. Extensive experiments conducted on benchmark datasets demonstrate that FVW-GCN consistently outperforms state-of-the-art baselines across several standard evaluation metrics, including recall, normalized discounted cumulative gain, and hit ratio. These results confirm the robustness and effectiveness of the proposed framework, highlighting its potential to support more accurate, diverse, and user-centric recommendation services in real-world applications.

推荐系统通过向跨领域（如电子商务、餐饮服务和数字媒体）的用户提供个性化建议，在减轻信息过载方面发挥着重要作用。近年来，基于图的方法，特别是那些利用图卷积网络（GCNs）的方法，通过建模高阶连接显示出强大的性能。然而，它们的有效性仍然受到三个关键挑战的限制：用户-项目交互的稀疏性，扭曲偏好建模的嘈杂或瞬态行为的存在，以及评论和产品描述中包含的上下文信息的利用不足。为了解决这些限制，我们提出了一个新的框架，称为模糊和变权图卷积网络（FVW-GCN）。该框架包含一个模糊关系建模模块，通过对预训练语言模型中提取的语义嵌入应用模糊c均值聚类来丰富邻接结构，从而提高稀疏和长尾项目的连通性。此外，还引入了变权GCN模块，其中调优GCN从采样子图中学习局部权矩阵，然后由调优GCN自适应地细化嵌入并抑制噪声信号。通过这种组合，FVW-GCN有效地加强了有意义的关系，同时减少了不可靠交互的影响。在基准数据集上进行的大量实验表明，FVW-GCN在几个标准评估指标上始终优于最先进的基线，包括召回率、标准化贴现累积增益和命中率。这些结果证实了所提出框架的鲁棒性和有效性，突出了其在现实应用中支持更准确、更多样化和以用户为中心的推荐服务的潜力。

{"title":"Fuzzy-enhanced variable weight graph convolutional networks for recommender systems","authors":"Wanna Cui, Hak-Keung Lam","doi":"10.1016/j.compeleceng.2026.110970","DOIUrl":"10.1016/j.compeleceng.2026.110970","url":null,"abstract":"<div><div>Recommender systems play an essential role in alleviating information overload by delivering personalized suggestions to users across domains such as e-commerce, restaurant services, and digital media. In recent years, graph-based approaches, particularly those leveraging graph convolutional networks (GCNs), have shown strong performance by modeling high-order connectivity. However, their effectiveness remains constrained by three critical challenges: the sparsity of user–item interactions, the presence of noisy or transient behaviors that distort preference modeling, and the underutilization of contextual information contained in reviews and product descriptions. To address these limitations, we propose a novel framework, termed fuzzy and variable weight graph convolutional network (FVW-GCN). The framework incorporates a fuzzy relation modeling module that enriches the adjacency structure by applying fuzzy C-means clustering to semantic embeddings extracted from pre-trained language models, thereby improving connectivity for sparse and long-tail items. In addition, a variable-weight GCN module is introduced, where a tuning GCN learns localized weight matrices from sampled subgraphs, which are then used by a tuned GCN to adaptively refine embeddings and suppress noisy signals. Through this combination, FVW-GCN effectively strengthens meaningful relations while reducing the influence of unreliable interactions. Extensive experiments conducted on benchmark datasets demonstrate that FVW-GCN consistently outperforms state-of-the-art baselines across several standard evaluation metrics, including recall, normalized discounted cumulative gain, and hit ratio. These results confirm the robustness and effectiveness of the proposed framework, highlighting its potential to support more accurate, diverse, and user-centric recommendation services in real-world applications.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"131 ","pages":"Article 110970"},"PeriodicalIF":4.9,"publicationDate":"2026-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145927372","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}

引用次数: 0

Attack a class of dynamic cryptosystem based on chaos 攻击一类基于混沌的动态密码系统

IF 4.9 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2026-01-08 DOI: 10.1016/j.compeleceng.2026.110965

Rong Zhou

This study presents a cryptanalysis of a dynamic image cryptosystem based on chaos, referred to as DIC-BOC. Using DIC-BOC as a case study, the work introduces an innovative concept — termed T-ADTC (Thought of Applying Database to Cryptanalysis) — specifically designed to mount attacks against various instances of DIC-BOC. The particular DIC-BOC under investigation is an enhanced version of a plaintext-independent cryptosystem, featuring two key improvements to its dynamic mechanism: (1) linking the chaotic sequence used for encryption directly to the plaintext during the permutation stage, and (2) incorporating dynamic ciphertext feedback into the diffusion process. These enhancements significantly boost security compared to the original scheme. Although the authors assert the robustness of DIC-BOC based on empirical tests, rigorous cryptanalysis reveals critical vulnerabilities that render it susceptible to the proposed T-ADTC attack. Guided by T-ADTC, the study further refines this specific DIC-BOC, achieving additional advancements. Moreover, T-ADTC is not limited to this instance; it can be generalized to evaluate other DIC-BOC variants and offers crucial insights for the future development of cryptographic systems. Both theoretical analysis and experimental results confirm the feasibility and effectiveness of the proposed approach.

本研究提出一种基于混沌的动态图像密码系统的密码分析方法，称为DIC-BOC。使用DIC-BOC作为案例研究，该工作引入了一个创新概念-称为T-ADTC（将数据库应用于密码分析的想法）-专门设计用于对各种DIC-BOC实例进行攻击。正在研究的特定DIC-BOC是一种独立于明文的密码系统的增强版本，其动态机制有两个关键改进：(1)在排列阶段将用于加密的混沌序列直接链接到明文，以及(2)将动态密文反馈纳入扩散过程。与原始方案相比，这些增强功能显著提高了安全性。尽管作者基于经验测试断言DIC-BOC的稳健性，但严格的密码分析揭示了使其容易受到提议的T-ADTC攻击的关键漏洞。在T-ADTC的指导下，该研究进一步完善了这种特定的DIC-BOC，取得了额外的进展。此外，T-ADTC并不局限于这种情况；它可以推广到评估其他DIC-BOC变体，并为加密系统的未来发展提供重要见解。理论分析和实验结果均证实了该方法的可行性和有效性。

{"title":"Attack a class of dynamic cryptosystem based on chaos","authors":"Rong Zhou","doi":"10.1016/j.compeleceng.2026.110965","DOIUrl":"10.1016/j.compeleceng.2026.110965","url":null,"abstract":"<div><div>This study presents a cryptanalysis of a dynamic image cryptosystem based on chaos, referred to as DIC-BOC. Using DIC-BOC as a case study, the work introduces an innovative concept — termed T-ADTC (Thought of Applying Database to Cryptanalysis) — specifically designed to mount attacks against various instances of DIC-BOC. The particular DIC-BOC under investigation is an enhanced version of a plaintext-independent cryptosystem, featuring two key improvements to its dynamic mechanism: (1) linking the chaotic sequence used for encryption directly to the plaintext during the permutation stage, and (2) incorporating dynamic ciphertext feedback into the diffusion process. These enhancements significantly boost security compared to the original scheme. Although the authors assert the robustness of DIC-BOC based on empirical tests, rigorous cryptanalysis reveals critical vulnerabilities that render it susceptible to the proposed T-ADTC attack. Guided by T-ADTC, the study further refines this specific DIC-BOC, achieving additional advancements. Moreover, T-ADTC is not limited to this instance; it can be generalized to evaluate other DIC-BOC variants and offers crucial insights for the future development of cryptographic systems. Both theoretical analysis and experimental results confirm the feasibility and effectiveness of the proposed approach.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"131 ","pages":"Article 110965"},"PeriodicalIF":4.9,"publicationDate":"2026-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145927512","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}

引用次数: 0

Affinity-based fuzzy twin random vector functional link network classifier 基于亲和的模糊双随机向量功能链接网络分类器

IF 4.9 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2026-01-08 DOI: 10.1016/j.compeleceng.2025.110923

Chittabarni Sarkar , Deepak Gupta , Rajat Subhra Goswami , Barenya Bikash Hazarika

In real-world, numerous leaf diseases are proliferating due to soil pollution and weather-related factors. Manual identification is slow and often ineffective. Identification hazards are created when noisy data and binary class imbalance problems are present. To address the noise and imbalanced data issue, several affinity and class probability-models were suggested, which reduce noise through regularization and handles class imbalance using affinity values from support vector data description (SVDD) and class probabilities from k-nearest neighbour (KNN). Minority samples with low affinity and probability receive less weight, while majority samples with higher values strongly influence the decision boundary. To enhance generalization an computational efficiency, an affinity and class probability-based fuzzy random vector functional link network (ACFRVFL) is introduced, combining fuzzy logic, SVDD, and KNN with RVFL. Moreover, an affinity and class probability-based fuzzy twin RVFL (ACFTRVFL) model is also suggested for improved performance. The study evaluates performance using various benchmark datasets.

在现实世界中，由于土壤污染和天气相关因素，许多叶片病害正在蔓延。手动识别是缓慢的，而且常常是无效的。当存在噪声数据和二元类不平衡问题时，会产生识别危害。为了解决噪声和不平衡数据问题，提出了几种亲和和类概率模型，这些模型通过正则化来降低噪声，并使用支持向量数据描述（SVDD）的亲和值和k近邻（KNN）的类概率来处理类不平衡。亲和性和概率较低的少数样本权重较小，而较高的多数样本对决策边界的影响较大。为了提高泛化和计算效率，将模糊逻辑、SVDD和KNN与RVFL相结合，提出了一种基于亲和和类概率的模糊随机向量功能链接网络（ACFRVFL）。此外，还提出了一种基于亲和性和类概率的模糊双RVFL （ACFTRVFL）模型来提高性能。该研究使用各种基准数据集评估性能。

{"title":"Affinity-based fuzzy twin random vector functional link network classifier","authors":"Chittabarni Sarkar , Deepak Gupta , Rajat Subhra Goswami , Barenya Bikash Hazarika","doi":"10.1016/j.compeleceng.2025.110923","DOIUrl":"10.1016/j.compeleceng.2025.110923","url":null,"abstract":"<div><div>In real-world, numerous leaf diseases are proliferating due to soil pollution and weather-related factors. Manual identification is slow and often ineffective. Identification hazards are created when noisy data and binary class imbalance problems are present. To address the noise and imbalanced data issue, several affinity and class probability-models were suggested, which reduce noise through regularization and handles class imbalance using affinity values from support vector data description (SVDD) and class probabilities from k-nearest neighbour (KNN). Minority samples with low affinity and probability receive less weight, while majority samples with higher values strongly influence the decision boundary. To enhance generalization an computational efficiency, an affinity and class probability-based fuzzy random vector functional link network (ACFRVFL) is introduced, combining fuzzy logic, SVDD, and KNN with RVFL. Moreover, an affinity and class probability-based fuzzy twin RVFL (ACFTRVFL) model is also suggested for improved performance. The study evaluates performance using various benchmark datasets.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"131 ","pages":"Article 110923"},"PeriodicalIF":4.9,"publicationDate":"2026-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145927373","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}

引用次数: 0

Federated learning in healthcare: Recent progress and challenges 医疗保健中的联邦学习：最近的进展和挑战

IF 4.9 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2026-01-07 DOI: 10.1016/j.compeleceng.2025.110924

Amara Miloudi , Abdelkader Laouid , Ahcène Bounceur , Mostefa Kara , Mohammed Mounir Bouhamed , Mohammad Hamoudeh , Insaf Kraidia

Federated Learning (FL) emerged as a transformative approach to collaborative model training in healthcare, enabling multiple institutions to develop robust Machine Learning models without compromising sensitive patient data. This review examines recent advances, applications, and challenges associated with FL in healthcare, focusing on its potential to enhance data security and privacy through the aggregation of decentralized models. A comprehensive literature review was conducted using databases including PubMed, Google Scholar, and Scopus, identifying 316 relevant publications, from which 23 were selected for detailed analysis. The findings highlight the applications of FL in critical healthcare areas, including oncology, infectious diseases, medical imaging, drug development, and personalized medicine. Although FL offers significant opportunities for precision medicine by managing fragmented and heterogeneous datasets, substantial challenges remain, particularly regarding data standardization, model convergence, and communication efficiency. This review also addresses crucial aspects such as privacy-preserving techniques, ethical compliance, and system scalability, emphasizing the need for interdisciplinary solutions. Ultimately, FL demonstrates significant potential to revolutionize healthcare by improving patient outcomes and accelerating medical research while maintaining strict regulatory compliance. Future research directions are discussed to overcome current barriers and advance the broader adoption of FL in healthcare applications.

联邦学习（FL）作为医疗保健领域协作模型培训的一种变革性方法出现，使多个机构能够在不损害敏感患者数据的情况下开发强大的机器学习模型。本文回顾了FL在医疗保健领域的最新进展、应用和挑战，重点关注其通过分散模型的聚合增强数据安全和隐私的潜力。利用PubMed、b谷歌Scholar、Scopus等数据库进行全面的文献综述，筛选出316篇相关文献，并从中选取23篇进行详细分析。研究结果强调了FL在关键医疗保健领域的应用，包括肿瘤学、传染病、医学成像、药物开发和个性化医疗。尽管FL通过管理碎片化和异构数据集为精准医疗提供了重要机会，但仍存在重大挑战，特别是在数据标准化、模型融合和通信效率方面。本文还讨论了隐私保护技术、道德合规和系统可扩展性等关键方面，强调了跨学科解决方案的必要性。最终，FL通过改善患者预后和加速医学研究，同时保持严格的法规遵从性，展示了革命性医疗保健的巨大潜力。讨论了未来的研究方向，以克服当前的障碍，并推动FL在医疗保健应用中的广泛采用。

{"title":"Federated learning in healthcare: Recent progress and challenges","authors":"Amara Miloudi , Abdelkader Laouid , Ahcène Bounceur , Mostefa Kara , Mohammed Mounir Bouhamed , Mohammad Hamoudeh , Insaf Kraidia","doi":"10.1016/j.compeleceng.2025.110924","DOIUrl":"10.1016/j.compeleceng.2025.110924","url":null,"abstract":"<div><div>Federated Learning (FL) emerged as a transformative approach to collaborative model training in healthcare, enabling multiple institutions to develop robust Machine Learning models without compromising sensitive patient data. This review examines recent advances, applications, and challenges associated with FL in healthcare, focusing on its potential to enhance data security and privacy through the aggregation of decentralized models. A comprehensive literature review was conducted using databases including PubMed, Google Scholar, and Scopus, identifying 316 relevant publications, from which 23 were selected for detailed analysis. The findings highlight the applications of FL in critical healthcare areas, including oncology, infectious diseases, medical imaging, drug development, and personalized medicine. Although FL offers significant opportunities for precision medicine by managing fragmented and heterogeneous datasets, substantial challenges remain, particularly regarding data standardization, model convergence, and communication efficiency. This review also addresses crucial aspects such as privacy-preserving techniques, ethical compliance, and system scalability, emphasizing the need for interdisciplinary solutions. Ultimately, FL demonstrates significant potential to revolutionize healthcare by improving patient outcomes and accelerating medical research while maintaining strict regulatory compliance. Future research directions are discussed to overcome current barriers and advance the broader adoption of FL in healthcare applications.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"131 ","pages":"Article 110924"},"PeriodicalIF":4.9,"publicationDate":"2026-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145927374","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}

引用次数: 0

A secure expert system framework for private function evaluation using functional encryption and multi-party computation 基于功能加密和多方计算的私有功能评估安全专家系统框架

IF 4.9 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2026-01-07 DOI: 10.1016/j.compeleceng.2025.110930

Rahat Naz , Jaydeep Howlader , Shahnawaz Ahmad

Cloud systems and edge-based systems have an increasing appetite for privacy-preserving computation over distributed sensitive data. Most existing cryptographic solutions don't perform well when executing complex inference tasks while hiding both the input data and the logic of the functions. This can be a serious shortcoming in particular areas, such as healthcare analytics and financial modeling, where data privacy and model protections are paramount. Although secure multiparty computation (SMPC) and functional encryption (FE) hold promise individually, current implementations are often either not scalable or not auditable from end to end in adversarial models. This work presents a hybrid framework that fuses FE with SMPC to enable private function evaluation (PFE) in decentralized environments. The architecture supports encrypted expert inference, leveraging a trust-weighted cryptographic consensus layer, dynamic key management, and function-specific policy enforcement. An adaptive fusion of secure execution and traceable audit logging ensures both privacy and compliance without sacrificing computational tractability. Experimental validation demonstrates that our system reduces decision latency by up to 18 % over standard FE baselines and improves leakage resistance under semi-honest and collusion-based attacks by 23 %, with auditability scores reaching 87 % in real-world simulation settings. By enabling the execution of confidential functions with built-in explainability and regulatory transparency, the proposed system lays the foundation for secure AI-as-a-service platforms. Its compatibility with edge deployments and extensibility toward zero-knowledge and post-quantum cryptography position it as a robust candidate for the next generation of trust-aware decentralized computation.

云系统和基于边缘的系统对分布式敏感数据的隐私保护计算的需求越来越大。大多数现有的加密解决方案在执行复杂的推理任务时都不能很好地执行，同时隐藏输入数据和函数的逻辑。在某些领域，这可能是一个严重的缺点，例如医疗保健分析和财务建模，在这些领域，数据隐私和模型保护至关重要。尽管安全多方计算（SMPC）和功能加密（FE）各自都有希望，但在对抗性模型中，当前的实现通常要么不可扩展，要么不可从端到端进行审计。这项工作提出了一个混合框架，将FE与SMPC融合在一起，在分散的环境中实现私有功能评估（PFE）。该体系结构支持加密专家推理，利用信任加权的加密共识层、动态密钥管理和特定于功能的策略实施。安全执行和可跟踪审计日志的自适应融合在不牺牲计算可跟踪性的情况下确保了隐私和遵从性。实验验证表明，我们的系统比标准FE基线减少了18%的决策延迟，并在半诚实和基于串通的攻击下提高了23%的泄漏阻力，在真实世界的模拟设置中可审计性得分达到87%。通过使机密功能的执行具有内置的可解释性和监管透明度，拟议的系统为安全的ai即服务平台奠定了基础。它与边缘部署的兼容性以及对零知识和后量子密码学的可扩展性使其成为下一代信任感知分散计算的健壮候选者。

{"title":"A secure expert system framework for private function evaluation using functional encryption and multi-party computation","authors":"Rahat Naz , Jaydeep Howlader , Shahnawaz Ahmad","doi":"10.1016/j.compeleceng.2025.110930","DOIUrl":"10.1016/j.compeleceng.2025.110930","url":null,"abstract":"<div><div>Cloud systems and edge-based systems have an increasing appetite for privacy-preserving computation over distributed sensitive data. Most existing cryptographic solutions don't perform well when executing complex inference tasks while hiding both the input data and the logic of the functions. This can be a serious shortcoming in particular areas, such as healthcare analytics and financial modeling, where data privacy and model protections are paramount. Although secure multiparty computation (SMPC) and functional encryption (FE) hold promise individually, current implementations are often either not scalable or not auditable from end to end in adversarial models. This work presents a hybrid framework that fuses FE with SMPC to enable private function evaluation (PFE) in decentralized environments. The architecture supports encrypted expert inference, leveraging a trust-weighted cryptographic consensus layer, dynamic key management, and function-specific policy enforcement. An adaptive fusion of secure execution and traceable audit logging ensures both privacy and compliance without sacrificing computational tractability. Experimental validation demonstrates that our system reduces decision latency by up to 18 % over standard FE baselines and improves leakage resistance under semi-honest and collusion-based attacks by 23 %, with auditability scores reaching 87 % in real-world simulation settings. By enabling the execution of confidential functions with built-in explainability and regulatory transparency, the proposed system lays the foundation for secure AI-as-a-service platforms. Its compatibility with edge deployments and extensibility toward zero-knowledge and post-quantum cryptography position it as a robust candidate for the next generation of trust-aware decentralized computation.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"131 ","pages":"Article 110930"},"PeriodicalIF":4.9,"publicationDate":"2026-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145927371","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}

引用次数: 0