Haoran Wang¹, Shuhong Yang², Kuan Shao², Tao Xiao², Zhenyong Zhang^2,*

CMC-Computers, Materials & Continua, Vol.86, No.1, pp. 1-18, 2026, DOI:10.32604/cmc.2025.069404 - 10 November 2025

Abstract With the rapid development of the Artificial Intelligence of Things (AIoT), convolutional neural networks (CNNs) have demonstrated potential and remarkable performance in AIoT applications due to their excellent performance in various inference tasks. However, the users have concerns about privacy leakage for the use of AI and the performance and efficiency of computing on resource-constrained IoT edge devices. Therefore, this paper proposes an efficient privacy-preserving CNN framework (i.e., EPPA) based on the Fully Homomorphic Encryption (FHE) scheme for AIoT application scenarios. In the plaintext domain, we verify schemes with different activation structures to determine the… More >

Ray-I Chang¹, Chia-Hui Wang^2,*, Yen-Ting Chang¹, Lien-Chen Wei²

CMC-Computers, Materials & Continua, Vol.85, No.1, pp. 503-518, 2025, DOI:10.32604/cmc.2025.068516 - 29 August 2025

Abstract As data analysis often incurs significant communication and computational costs, these tasks are increasingly outsourced to cloud computing platforms. However, this introduces privacy concerns, as sensitive data must be transmitted to and processed by untrusted parties. To address this, fully homomorphic encryption (FHE) has emerged as a promising solution for privacy-preserving Machine-Learning-as-a-Service (MLaaS), enabling computation on encrypted data without revealing the plaintext. Nevertheless, FHE remains computationally expensive. As a result, approximate homomorphic encryption (AHE) schemes, such as CKKS, have attracted attention due to their efficiency. In our previous work, we proposed RP-OKC, a CKKS-based clustering… More >

Lingling Wu¹, Xu An Wang^1,2,*, Jiasen Liu¹, Yunxuan Su¹, Zheng Tu¹, Wenhao Liu¹, Haibo Lei¹, Dianhua Tang³, Yunfei Cao³, Jianping Zhang³

CMC-Computers, Materials & Continua, Vol.85, No.1, pp. 89-119, 2025, DOI:10.32604/cmc.2025.064346 - 29 August 2025

Abstract Due to the rapid advancement of information technology, data has emerged as the core resource driving decision-making and innovation across all industries. As the foundation of artificial intelligence, machine learning(ML) has expanded its applications into intelligent recommendation systems, autonomous driving, medical diagnosis, and financial risk assessment. However, it relies on massive datasets, which contain sensitive personal information. Consequently, Privacy-Preserving Machine Learning (PPML) has become a critical research direction. To address the challenges of efficiency and accuracy in encrypted data computation within PPML, Homomorphic Encryption (HE) technology is a crucial solution, owing to its capability to… More >

Chenxin Lin¹, Qun Zhou¹, Zhan Wang^2,*, Ximing Fan², Yaochang Xu², Yijia Xu²

CMC-Computers, Materials & Continua, Vol.84, No.3, pp. 5859-5877, 2025, DOI:10.32604/cmc.2025.065496 - 30 July 2025

Abstract False Data Injection Attack (FDIA), a disruptive cyber threat, is becoming increasingly detrimental to smart grids with the deepening integration of information technology and physical power systems, leading to system unreliability, data integrity loss and operational vulnerability exposure. Given its widespread harm and impact, conducting in-depth research on FDIA detection is vitally important. This paper innovatively introduces a FDIA detection scheme: A Protected Federated Deep Learning (ProFed), which leverages Federated Averaging algorithm (FedAvg) as a foundational framework to fortify data security, harnesses pre-trained enhanced spatial-temporal graph neural networks (STGNN) to perform localized model training and More >

Peizheng Lai¹, Minqing Zhang^1,2,*, Yixin Tang¹, Ya Yue¹, Fuqiang Di^1,2

CMC-Computers, Materials & Continua, Vol.84, No.2, pp. 2935-2957, 2025, DOI:10.32604/cmc.2025.065887 - 03 July 2025

Abstract Federated Learning (FL) has emerged as a promising distributed machine learning paradigm that enables multi-party collaborative training while eliminating the need for raw data sharing. However, its reliance on a server introduces critical security vulnerabilities: malicious servers can infer private information from received local model updates or deliberately manipulate aggregation results. Consequently, achieving verifiable aggregation without compromising client privacy remains a critical challenge. To address these problem, we propose a reversible data hiding in encrypted domains (RDHED) scheme, which designs joint secret message embedding and extraction mechanism. This approach enables clients to embed secret messages… More >

Dain Lee^1,#, Hojune Shin^1,#, Jihyeon Choi¹, Younho Lee^1,2,*

CMC-Computers, Materials & Continua, Vol.84, No.2, pp. 3673-3705, 2025, DOI:10.32604/cmc.2025.064161 - 03 July 2025

Abstract In this study, we investigated privacy-preserving ID3 Decision Tree (PPID3) training and inference based on fully homomorphic encryption (FHE), which has not been actively explored due to the high computational cost associated with managing numerous child nodes in an ID3 tree. We propose HEaaN-ID3, a novel approach to realize PPID3 using the Cheon-Kim-Kim-Song (CKKS) scheme. HEaaN-ID3 is the first FHE-based ID3 framework that completes both training and inference without any intermediate decryption, which is especially valuable when decryption keys are inaccessible or a single-cloud security domain is assumed. To enhance computational efficiency, we adopt a… More >

Ronglei Hu¹, Chuce He^1,2, Sihui Liu¹, Dong Yao¹, Xiuying Li¹, Xiaoyi Duan^1,*

CMC-Computers, Materials & Continua, Vol.84, No.1, pp. 937-956, 2025, DOI:10.32604/cmc.2025.062542 - 09 June 2025

Abstract Ciphertext data retrieval in cloud databases suffers from some critical limitations, such as inadequate security measures, disorganized key management practices, and insufficient retrieval access control capabilities. To address these problems, this paper proposes an enhanced Fully Homomorphic Encryption (FHE) algorithm based on an improved DGHV algorithm, coupled with an optimized ciphertext retrieval scheme. Our specific contributions are outlined as follows: First, we employ an authorization code to verify the user’s retrieval authority and perform hierarchical access control on cloud storage data. Second, a triple-key encryption mechanism, which separates the data encryption key, retrieval authorization key, More >

Hongliang Tian, Zuoqing Li^*

CMC-Computers, Materials & Continua, Vol.82, No.3, pp. 3983-4002, 2025, DOI:10.32604/cmc.2025.059103 - 06 March 2025

Abstract Low data encryption efficiency and inadequate security are two issues with the current blockchain cross-chain transaction protection schemes. To address these issues, a blockchain cross-chain transaction protection scheme based on Fully Homomorphic Encryption (FHE) is proposed. In the proposed scheme, the functional relationship is established by Box-Muller, Discrete Gaussian Distribution Function (DGDF) and Uniform Random Distribution Function (URDF) are used to improve the security and efficiency of key generation. Subsequently, the data preprocessing function is introduced to perform cleaning, deduplication, and normalization operations on the transaction data of multi-key signature, and it is classified into… More >

Cong Shen^1,*, Wei Zhang^1,2,*, Tanping Zhou^1,2, Yiming Zhang¹, Lingling Zhang³

CMC-Computers, Materials & Continua, Vol.80, No.3, pp. 4729-4748, 2024, DOI:10.32604/cmc.2024.054434 - 12 September 2024

Abstract With the increasing awareness of privacy protection and the improvement of relevant laws, federal learning has gradually become a new choice for cross-agency and cross-device machine learning. In order to solve the problems of privacy leakage, high computational overhead and high traffic in some federated learning schemes, this paper proposes a multiplicative double privacy mask algorithm which is convenient for homomorphic addition aggregation. The combination of homomorphic encryption and secret sharing ensures that the server cannot compromise user privacy from the private gradient uploaded by the participants. At the same time, the proposed TQRR (Top-Q-Random-R) More >

Hao Sun^*, Xiubo Chen, Kaiguo Yuan

CMC-Computers, Materials & Continua, Vol.79, No.2, pp. 2361-2373, 2024, DOI:10.32604/cmc.2024.049159 - 15 May 2024

Abstract Federated learning ensures data privacy and security by sharing models among multiple computing nodes instead of plaintext data. However, there is still a potential risk of privacy leakage, for example, attackers can obtain the original data through model inference attacks. Therefore, safeguarding the privacy of model parameters becomes crucial. One proposed solution involves incorporating homomorphic encryption algorithms into the federated learning process. However, the existing federated learning privacy protection scheme based on homomorphic encryption will greatly reduce the efficiency and robustness when there are performance differences between parties or abnormal nodes. To solve the above… More >