Article
Computer Science, Hardware & Architecture
Zhenjun Tang, Mengzhu Yu, Heng Yao, Hanyun Zhang, Chunqiang Yu, Xianquan Zhang
Summary: Image hashing using quaternion singular value decomposition (QSVD) is proposed in this paper, which extracts stable and discriminative features from CIE L*a*b* color space. Experimental results show its efficiency and good discrimination, outperforming some state-of-the-art algorithms in classification performance.
Article
Computer Science, Artificial Intelligence
Xinran Li, Mengqi Guo, Zichi Wang, Jian Li, Chuan Qin
Summary: This article proposes a powerful image hashing method for encrypted images, which can extract hash sequences from the encrypted version of an image without decryption, to protect the privacy of image content. The method encrypts the plaintext image using the Paillier cryptosystem, and then extracts the hash sequence through Walsh-Hadamard transform and histogram statistics. In the encrypted domain, image owners can efficiently authenticate their images through a cloud server without disclosing the image content. Compared with traditional hashing methods designed for plaintext domain, our method achieves satisfactory privacy-preserving performance and better image authentication performance.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE
(2023)
Article
Computer Science, Information Systems
Sebastiano Battiato, Oliver Giudice, Francesco Guarnera, Giovanni Puglisi
Summary: The paper introduces a novel FQE technique for JPEG double compressed images, which combines machine learning and statistical analysis methods, and has been shown to outperform existing solutions in different challenging scenarios.
Article
Computer Science, Artificial Intelligence
Myung-Joon Kwon, Seung-Hun Nam, In-Jae Yu, Heung-Kyu Lee, Changick Kim
Summary: This article introduces a method using a neural network to detect and localize image manipulation by analyzing compression artifacts using discrete cosine transform (DCT) coefficients to distinguish between authentic and tampered regions. Additionally, a Compression Artifact Tracing Network is introduced, which combines image acquisition artifacts and compression artifacts, and significantly improves the detection and localization of tampered regions.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2022)
Article
Computer Science, Artificial Intelligence
Runwen Hu, Shijun Xiang
Summary: This article presents a new cover-lossless robust image watermarking method by embedding a watermark into low-order Zernike moments, achieving good performance against geometric deformations.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Computer Science, Artificial Intelligence
Madhumita Paul, Arnab Jyoti Thakuria, Ram Kumar Karsh, Fazal Ahmed Talukdar
Summary: The paper proposes an image hashing technique based on convolutional stacked denoising auto-encoders (CSDAEs) and incorporates a blind geometric correction method to detect composite RST distortions in images.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Engineering, Electrical & Electronic
Xiaoqi Lu, Jianwei Yang
Summary: Zernike moments (ZMs) are widely used orthogonal moments, but low-order ZMs have limitations in describing small size images. Fractional Zernike moments (FrZMs) can handle small size images, but high-order FrZMs suffer from numerical instability. To overcome these issues, transformed Zernike moments (TZMs) and logarithmic Zernike moments (LoZMs) are introduced.
DIGITAL SIGNAL PROCESSING
(2023)
Article
Computer Science, Information Systems
Mohamed Dahmane
Summary: This work proposes an effective perceptual entanglement-based approach for image authentication, which ensures image integrity through local encoding and global entanglement, and is capable of pinpointing the location of tampered pixels.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Thomas Theodoridis, Kostas Loumponias, Nicholas Vretos, Petros Daras
Summary: Most neural network architectures in computer vision consist of the same building blocks, but a generalization of the traditional average pooling operator using Zernike moments has shown superior performance on experimental datasets compared to baseline approaches. Significant gains in classification accuracy can be achieved with only a modest increase in training time.
Review
Computer Science, Information Systems
Abdul Subhani Shaik, Ram Kumar Karsh, Mohiul Islam, Rabul Hussain Laskar
Summary: This paper discusses the importance of image hashing technology in multimedia security applications, focusing on key challenges and design parameters in hashing schemes. It summarizes the existing literature on hashing-based image authentication techniques, explores different algorithm performance and comparisons between datasets.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Petra Gomez-Kramer, Kais Rouis, Azise Oumar Diallo, Mickael Coustaty
Summary: Automatic document authentication is a complex task that aims to prove the authenticity of a document through its content fingerprint. This article presents a method based on the Delaunay layout descriptor, which combines global and local matching, to effectively compare and authenticate layouts.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Theory & Methods
Arindam Kar, Sourav Pramanik, Arghya Chakraborty, Debotosh Bhattacharjee, Edmond S. L. Ho, Hubert P. H. Shum
Summary: In this work, a novel face recognition method called LMZMPM is proposed, which is invariant to various factors such as illumination, scaling, noise, and incorporates a hybrid similarity measure for classification. The study demonstrates the reliability of LMZMPM under different conditions and shows excellent performance in face recognition.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2021)
Article
Computer Science, Artificial Intelligence
Yulong Wang, Kit Ian Kou, Cuiming Zou, Yuan Yan Tang
Summary: The proposed robust quaternion valued sparse representation (RQVSR) method in a fully quaternion valued setting effectively addresses the challenges of sparse signal recovery and color image reconstruction, by mitigating the impact of data noise and outliers. The method overcomes the difficulties raised by quaternion multiplication noncommutativity and demonstrates effectiveness and robustness in experiments.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Computer Science, Theory & Methods
Zhuohao Jia, Simon Liao
Summary: This article presents a novel GPU-based method for efficiently computing high-order Zernike moments and demonstrates its effectiveness in computing 500-order Zernike moments within 0.5 seconds for a 512x512 image.
JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Yao Xiao, Wei Zhang, Xiangguang Dai, Xiangqin Dai, Nian Zhang
Summary: In this paper, a robust supervised hashing framework, called Robust Supervised Discrete Hashing (RSDH), is proposed based on the Cauchy loss function and Supervised Discrete Hashing (SDH) to learn a subspace consisted of binary codes. RSDH can reduce outliers and noise of the hashing codes and achieve better retrieval performance.
Article
Engineering, Electrical & Electronic
Zhixia Zhang, Yang Cao, Zhihua Cui, Wensheng Zhang, Jinjun Chen
Summary: A novel weight-based ensemble machine learning algorithm was designed to identify abnormal messages in vehicular Controller Area Network (CAN) bus network, along with a model based on many-objective optimization for intrusion detection. Experimental results showed significant improvements in security and performance.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2021)
Article
Computer Science, Information Systems
Zhihua Cui, Xuechun Jing, Peng Zhao, Wensheng Zhang, Jinjun Chen
Summary: This study proposes a post-processing strategy for subspace clustering of hyperspectral image data to balance sparsity and connectivity, and experimental results demonstrate its effectiveness in improving clustering accuracy in the Internet of Things.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Information Systems
Xingjuan Cai, Shaojin Geng, Di Wu, Jianghui Cai, Jinjun Chen
Summary: The rapid development of IoT leads to unprecedented data demand and security challenges. Multicloud platform, as a high-performance secure computing platform, can address data processing and security issues to some extent.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Theory & Methods
Ying Zhao, Jinjun Chen
Summary: This article summarizes and analyzes the application of differential privacy solutions in protecting unstructured data, including various privacy models and mechanisms, as well as the challenges they face. It also discusses the privacy guarantees of these methods against AI attacks and utility losses, and proposes several possible directions for future research.
ACM COMPUTING SURVEYS
(2022)
Article
Computer Science, Artificial Intelligence
Xingjuan Cai, Jiangjiang Zhang, Zhenhu Ning, Zhihua Cui, Jinjun Chen
Summary: The article presents an improved many-objective fuzzy decision-making model with human participation for coal production prediction, including five objective functions, and a novel multistage many-objective optimization algorithm to adjust relevant model parameters. The algorithm involves three stages of optimization and aims to achieve a balance of convergence and diversity during population evolution. Results show that the proposed optimization algorithm outperforms other advanced many-objective algorithms in terms of convergence and diversity for coal fuzzy decision-making problems.
IEEE TRANSACTIONS ON FUZZY SYSTEMS
(2021)
Article
Automation & Control Systems
Xingjuan Cai, Shaojin Geng, Jingbo Zhang, Di Wu, Zhihua Cui, Wensheng Zhang, Jinjun Chen
Summary: The industrial Internet of Things relies on large amounts of data for efficient control of the physical world, but faces challenges in data security. Blockchain technology can support data security and privacy preservation, while sharding technology can improve network throughput and scalability. However, the effectiveness of sharding is still challenging.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Computer Science, Information Systems
Kai Zhang, Jiao Tian, Hongwang Xiao, Ying Zhao, Wenyu Zhao, Jinjun Chen
Summary: Blockchain has attracted attention from the IoT research community due to its decentralization and consistency. However, the accessibility of all nodes to the chain data raises privacy concerns. To address this issue, we propose a novel LDP mechanism that splits and perturbs input numerical data using digital bits, without requiring a fixed input range and large data volume. Our adaptive privacy budget allocation model significantly reduces the deviation of the perturbation function and provides high data utility while maintaining privacy.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Immunology
Kai Zhang, Lei Gao, Hai-xu Wang, Lei Ye, Yan-yan Shi, Wu-yan Yang, Ya-nan Li, Yan Li
Summary: The study found that IL-18 expression levels were significantly increased in NP tissues of both IVDD patients and mouse models. Treatment with Ad-sh-IL-18 reversed IVDD progression in mice models and increased levels of Aggrecan and Collagen II in NP cells. Ad-sh-IL-18 was also found to inhibit NP cell apoptosis by regulating the caspase-3/9 pathway.
IMMUNOLOGICAL INVESTIGATIONS
(2022)
Article
Automation & Control Systems
Jun Feng, Laurence T. Yang, Ronghao Zhang, Weizhong Qiang, Jinjun Chen
Summary: In this article, a novel privacy preserving HOBI-Lanczos approach using tensor train in cloud-fog computing is proposed for industrial data applications. The proposed approach allows for secure industrial data analysis without compromising users' privacy, and its superiority is demonstrated through experiments.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Article
Computer Science, Information Systems
Junlin Ouyang, Jingtao Huang, Xingzi Wen, Zhuhong Shao
Summary: This paper proposes a semi-fragile watermarking tamper localization method based on quaternion discrete Fourier transform (QDFT) and multi-view fusion. The method embeds two watermarks in the QDFT domain to improve resistance to geometric attacks and integrity protection of host images. By using global information and local smoothing cues, multi-scale candidate maps with real values are obtained instead of binary maps. Local adaptive fusion is then performed to obtain a consistent single tampering map. Experimental results show that the proposed method provides better resistance to signal processing attacks and improves the F-measure value of tamper localization compared to state-of-the-art methods.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Engineering, Multidisciplinary
Zhihua Cui, Zhixia Zhang, Zhaoming Hu, Shaojin Geng, Jinjun Chen
Summary: Cyber-Physical Social System (CPSS) is an emerging paradigm that offers efficient, convenient, and personalized services to humans. However, the explosive growth of user data has made dealing with massive and high-dimensional data a significant challenge for CPSS services. This paper addresses the issue of redundant attributes in high-dimensional data by optimizing the vision model using intelligent optimization technology. A collaboration mechanism (MaOEA-CM) is designed to support the model. Experimental results demonstrate that the proposed algorithm and model greatly improve the accuracy of data processing in CPSS.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2022)
Article
Computer Science, Information Systems
Muneeb Ul Hassan, Mubashir Husain Rehmani, Jinjun Chen
Summary: Over the past decade, blockchain technology has gained significant attention due to its integration with various everyday applications of modern information and communication technologies (ICT). The peer-to-peer (P2P) architecture of blockchain enhances these applications by providing strong security and trust-oriented guarantees. However, recent research has shown that blockchain networks may still face security, privacy, and reliability issues. In this article, we provide a comprehensive survey on the integration of anomaly detection models in blockchain technology. We discuss the role of anomaly detection in ensuring security, present evaluation metrics and requirements, survey various models, and highlight future research directions.
IEEE COMMUNICATIONS SURVEYS AND TUTORIALS
(2023)
Article
Computer Science, Artificial Intelligence
Ying Zhao, Dong Yuan, Jia Tina Du, Jinjun Chen
Summary: Directional distribution analysis is essential for abstracting dispersion and orientation of spatial datasets, but it must be used cautiously to protect individuals' privacy. There is a tension between accurate directional distribution results and location privacy. In this paper, we propose a geo-ellipse-indistinguishability privacy notion to protect individual location data and present elliptical privacy mechanisms based on gamma distribution and multivariate normal distribution. The empirical evaluation shows that our proposed elliptical approach achieves significantly higher directional distribution utility compared to circular noise function based methods.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Computer Science, Cybernetics
Xingjuan Cai, Wanwan Guo, Mengkai Zhao, Zhihua Cui, Jinjun Chen
Summary: This article proposes a knowledge graph-based many-objective model for explainable social recommendation (KGMESR), which considers the explainability, accuracy, novelty, and content quality of social recommendation results. The model utilizes social behavior information to calculate user similarity and quantifies the explainability of results using entity vectors and embedding vectors. A many-objective recommendation algorithm based on the partition deletion strategy is designed for efficiency. Experimental results demonstrate preferable recommendation results and two case studies affirm the explainability of the proposed model.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2023)
Article
Telecommunications
Muneeb Ul Hassan, Mubashir Husain Rehmani, Jinjun Chen
Summary: This paper discusses the research on decentralized auctions for energy trading. Blockchain, as a new paradigm, brings both trust and challenges of high computation and communication complexity. There is a need to develop greener and computational-friendly auctions. The paper provides motivation and design requirements for decentralized auctions, and analyzes existing technical works on blockchain-based energy auctions from a green perspective. Finally, challenges and possible future research directions are summarized.
IEEE TRANSACTIONS ON GREEN COMMUNICATIONS AND NETWORKING
(2022)