Article
Computer Science, Information Systems
Qingxuan Wang, Chi Cheng, Rui Xu, Jintai Ding, Zhe Liu
Summary: The authors introduce the DOPIV scheme, which allows a data owner to delegate a proxy to generate data signatures and outsource them to a cloud server. They use a third-party auditor to verify the integrity of the outsourced data. However, the authors discover vulnerabilities in DOPIV that enable the cloud server to delete data without being noticed. They propose a simple and efficient solution to thwart this attack while maintaining all the claimed features of DOPIV.
IEEE TRANSACTIONS ON SERVICES COMPUTING
(2022)
Article
Computer Science, Information Systems
Peng Gao, Hanlin Zhang, Jia Yu, Jie Lin, Xiaopeng Wang, Ming Yang, Fanyu Kong
Summary: This article addresses the issue of low efficiency in training and recognizing object recognition on hyperspectral remote sensing images on resource-constrained devices, proposing a secure and efficient scheme to outsource the task to untrustworthy cloud servers. The scheme protects the privacy of computation input and output and effectively detects misbehavior of the cloud server with optimal probability 1, ensuring security and efficiency.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Information Systems
Xin Sun, Chengliang Tian, Weizhong Tian, Yan Zhang
Summary: This paper investigates cloud-aided compressed sensing reconstruction algorithms and proposes a new privacy-enhanced and verifiable CSR outsourcing algorithm. Compared to previous work, our design has advantages in security, privacy preservation, and computational efficiency.
Article
Computer Science, Hardware & Architecture
Jin Li, Heng Ye, Tong Li, Wei Wang, Wenjing Lou, Y. Thomas Hou, Jiqiang Liu, Rongxing Lu
Summary: This article discusses the application of differential privacy in data privacy protection and proposes two schemes for outsourcing differential privacy. These schemes effectively address the issues of current differential privacy techniques in adapting to different tasks and budgets, and their effectiveness is verified through experiments.
IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING
(2022)
Article
Computer Science, Information Systems
Xiuli Chai, Jiangyu Fu, Zhihua Gan, Yang Lu, Yushu Zhang, Daojun Han
Summary: This article presents a new medical data transmission framework based on semi-tensor product compressed sensing (STP-CS) and hybrid cloud to address the issues of collection, storage, and transmission of medical data. Authentication information is embedded into the insignificant area of the medical image through edge detection to protect data authenticity. STP-CS is used to measure and encrypt the medical image, improving data transmission efficiency. An adaptive cyclic shift diffusion algorithm based on chaotic sequence is used to effectively diffuse the measurement results for enhanced image data security. Encoding is applied for tamper-proof authentication of quantized measurement values. Simulation results demonstrate the effectiveness of the proposed medical data transmission scheme in improving image reconstruction, transmission efficiency, and security.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Information Systems
Jia Duan, Jiantao Zhou, Yuanman Li
Summary: This work addresses the issue of secure outsourcing large-scale nonnegative matrix factorization (NMF) to the cloud by proposing a scheme that allows clients to verify results with small overhead. The protection of input matrix is achieved through a random permutation and scaling encryption mechanism, and a single-round verification strategy is proposed based on the iterative nature of NMF computation. Theoretical and experimental results demonstrate the superior performance of the proposed scheme.
IEEE TRANSACTIONS ON SERVICES COMPUTING
(2021)
Article
Computer Science, Information Systems
Xiulan Li, Jingguo Bi, Chengliang Tian, Hanlin Zhang, Jia Yu, Yanbin Pan
Summary: This article highlights the importance of solving quadratic congruence equations in secure Internet of Things applications. Two passive attacks are presented to demonstrate the insecurity of previous outsourcing algorithms. To address this issue, the authors propose an improved outsourcing algorithm that is efficient and protects the privacy of actual inputs and outputs.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Engineering, Multidisciplinary
Yishun Liu, Keke Huang, Chunhua Yang, Zhen Wang
Summary: Currently, the network model is a common framework for representing complex systems, and its structure is essential for controlling and applying networked systems. With the advent of the Big Data era, the scale of network structures is expanding rapidly. However, traditional centralized reconstruction methods are not practical due to the high computing resource requirements. To address this challenge, a distributed local reconstruction method is proposed for unweighted networks. By introducing the ADMM method, the complex reconstruction problem is decomposed into multiple subproblems, reducing the need for computing resources. In addition, a binary constraint is introduced to ensure reconstruction accuracy based on network structure characteristics. Extensive experiments demonstrate the superiority of the proposed method in reconstructing networks of different scales and types with limited computing resources, as well as its accuracy and robustness against noise.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2023)
Article
Computer Science, Information Systems
Yan He, Liang Feng Zhang
Summary: This study proposes a multi-matrix verifiable computation scheme that allows secure outsourcing of matrix function computation. Compared to the previous best known scheme, it is roughly m times faster and has lower communication cost in both client-side and server-side computation.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Hui Bai, Xixun Yu, Zheng Yan, Jialei Zhang, Laurence T. Yang
Summary: The current research on machine learning-based intelligent routing focuses on algorithm design and performance optimization, and the deployment in practice remains a pressing issue. Existing deep learning-based intelligent routing algorithms suffer from a high computational cost that is hard to be afforded by routers. However, outsourcing deep learning-based intelligent routing computations to the cloud becomes a feasible solution to support intelligent routing.
INFORMATION SCIENCES
(2023)
Article
Chemistry, Analytical
Mingyang Song, Yingpeng Sang
Summary: This paper introduces a secure outsourcing algorithm for computing the determinant of large matrices under a malicious cloud model. It protects the privacy of the original matrix by applying row/column permutation and other transformations, and utilizes a new verification method to resist malicious cheating.
Article
Computer Science, Information Systems
Mirella Muhic, Lars Bengtsson, Jonny Holmstrom
Summary: The continuous use of cloud computing and cloud sourcing has been overlooked in research compared to its adoption. More research is needed on the continuous use of cloud computing, as there are indications that the benefits of cloud sourcing are not easily realized by companies. This study contributes to the literature on cloud computing by providing one of the first examinations of the organizational-level processes in the continuance use of cloud computing. The findings highlight the existence of management process barriers and emphasize their importance in guiding the strategic direction of cloud computing and enabling cloud-related innovation.
INFORMATION & MANAGEMENT
(2023)
Review
Chemistry, Multidisciplinary
Rui Wang, Wanlin Zhang, Saisai Wang, Tonglong Zeng, Xiaohua Ma, Hong Wang, Yue Hao
Summary: This article systematically presents the requirements, mechanisms, and implementation methods of memristor-based compressed sensing (CS) technology, as well as its potential in all-in-one compression and encryption. The article points out the lack of a comprehensive overview of memristor-based CS techniques.
Article
Computer Science, Artificial Intelligence
Xiaofeng Chen, Hui Li, Jin Li, Qian Wang, Xinyi Huang, Willy Susilo, Yang Xiang
Summary: This study presents a new verifiable database (VDB) scheme that supports all updating operations and introduces a new primitive tool called Committed Invertible Bloom Filter (CIBF).
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2021)
Article
Computer Science, Information Systems
Hao Ren, Hongwei Li, Dongxiao Liu, Guowen Xu, Nan Cheng, Xuemin Shen
Summary: In this paper, an efficient verifiable deep packet inspection (EV-DPI) scheme is proposed to address privacy concerns in outsourced middlebox services. The scheme utilizes a two-layer architecture with non-collusion cloud servers, preserving packet privacy and confidentiality of inspection rules. Experimental results on the Amazon Cloud demonstrate the high efficiency and strong control of the proposed EV-DPI scheme.
IEEE TRANSACTIONS ON CLOUD COMPUTING
(2022)
Article
Computer Science, Hardware & Architecture
Nan Sun, Jun Zhang, Shang Gao, Leo Yu Zhang, Seyit Camtepe, Yang Xiang
Summary: With the rapid increase of cybersecurity attacks and their significant impact, the amount of cybersecurity-related information has surged. This article proposes an innovative cybersecurity retrieval scheme that uses semantic contents and hidden metadata for automatic indexing and searching of cybersecurity information. A novel cybersecurity search engine is implemented to demonstrate effective and understandable retrieval based on the proposed schema. Comprehensive performance evaluation is conducted on real-world datasets to validate the algorithms and techniques developed for cybersecurity information retrieval. This new engine enables augmented search, cybersecurity analytics, and visualization, aiming to provide direct and efficient results for obtaining and truly understanding cybersecurity information.
IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING
(2023)
Article
Acoustics
Juan Zhao, Tianrui Zong, Yong Xiang, Longxiang Gao, Guang Hua, Keshav Sood, Yushu Zhang
Summary: In this paper, a robust watermarking method for stereo signals is proposed, based on novel features SSVS and SSVD generated using DCT and SVD. The method achieves higher embedding rate and robustness while improving perceptual quality.
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
(2023)
Article
Computer Science, Information Systems
Ruoyu Zhao, Yushu Zhang, Rushi Lan, Zhongyun Hua, Yong Xiang
Summary: With the widespread use of the Internet of Things (IoT), privacy concerns have emerged as a significant issue due to the collection of user data by IoT devices. This article focuses on the protection of image privacy in the context of green IoT. A novel scheme called heterogeneous and customized cost-efficient reversible image degradation is proposed, which takes into consideration privacy characteristics and diverse user requirements. The scheme aims to achieve personalized privacy protection while maintaining cost effectiveness by preserving visual content in privacy-protected images and improving image compression efficiency.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Information Systems
Nai Wang, Junjun Chen, Di Wu, Wencheng Yang, Yong Xiang, Atul Sajjanhar
Summary: The IoT concept has become popular due to advancements in electronic chip manufacturing and networking hardware. By combining end devices and networking techniques, it is possible to use higher-level machine learning models like Federated Learning and Knowledge Distillation in IoT systems. However, ensuring security in network communications is crucial for system scalability and effectiveness.
JOURNAL OF INFORMATION SECURITY AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Yushu Zhang, Zhibin Fu, Shuren Qi, Mingfu Xue, Zhongyun Hua, Yong Xiang
Summary: In this work, an efficient feature enhancement network is proposed to locate the inpainted regions in the digital image. First, an artifact enhancement block is designed to effectively capture the traces left by diffusion or exemplar-based inpainting. Then, the VGGNet is used as a feature extractor to describe advanced and low-resolution features. Extensive experimental evaluations confirm the usefulness of the proposed method.
IEEE TRANSACTIONS ON BIG DATA
(2023)
Article
Computer Science, Artificial Intelligence
Chenhong Luo, Yong Wang, Bo Li, Hanyang Liu, Pengyu Wang, Leo Yu Zhang
Summary: Recommender systems search user preferences based on historical ratings and recommend items of interest. However, natural noises in the ratings can mislead the recommendations. Different methods have been proposed to handle natural noises, but they introduce new problems. To address this, we propose a new approach that detects natural noises based on user and item classifications and corrects them using probability-weighted threshold values. Experimental results show that our method effectively corrects natural noise and improves recommendation quality.
Proceedings Paper
Computer Science, Artificial Intelligence
Mengyao Ma, Yanjun Zhang, M. A. P. Chamikara, Leo Yu Zhang, Mohan Baruwal Chhetri, Guangdong Bai
Summary: Federated learning (FL) is vulnerable to poisoning membership inference attacks (MIA), and existing server-side robust aggregation algorithms (AGRs) are insufficient in mitigating these attacks. Therefore, a new client-side defense mechanism called LoDen is proposed to detect suspicious privacy attacks and mitigate poisoning MIA. Experimental evaluation shows that LoDen consistently achieves a 0% missing rate in detecting poisoning MIA and reduces the success rate of these attacks to 0% in most cases.
PROCEEDINGS OF THE 2023 ACM ASIA CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY, ASIA CCS 2023
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Xiaomei Zhang, Zhaoxi Zhang, Qi Zhong, Xufei Zheng, Yanjun Zhang, Shengshan Hu, Leo Yu Zhang
Summary: A novel textual adversarial example detection method, MLMD, based on masked language model is proposed to produce distinguishable signals between normal and adversarial examples. Experimental results demonstrate the strong performance of MLMD on multiple benchmark datasets.
PROCEEDINGS OF THE 2023 ACM ASIA CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY, ASIA CCS 2023
(2023)
Article
Computer Science, Theory & Methods
Hao Sun, Xiaofan Yang, Lu-Xing Yang, Kaifan Huang, Gang Li
Summary: Advanced persistent threat (APT) is a severe threat to modern organizations and artificial APT defense is recognized as essential. There are two ways of artificial APT defenses: continuous artificial defense (CAD) and impulsive artificial defense (IAD), where IAD is superior in terms of overall service cost. This paper addresses the development of a cost-effective IAD policy and presents an iterative algorithm for solving the optimal impulsive control model.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2023)
Article
Computer Science, Artificial Intelligence
Yushu Zhang, Zhibin Fu, Shuren Qi, Mingfu Xue, Xiaochun Cao, Yong Xiang
Summary: To address the misuse of Photoshop inpainting tools, we propose a novel method called PS-Net to localize the inpainted regions in images. PS-Net consists of a primary network and a secondary network, which successfully identify the forged regions by mining frequency clues and enhancing feature weights. Experimental results demonstrate that PS-Net outperforms several state-of-the-art solutions in localization ability.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Yongxiang Li, Dezhong Peng, Yong Xiang, Qingchuan Tao, Zhong Yuan
Summary: Most traditional blind source separation (BSS) methods assume that source signals are independent, but many signals in the real world are interrelated. This study proposes a new BSS method for dependent signals that relies on the relaxed sparsity of sources. The observed signals are distributed in a specific subspace based on the representation relation in the time-frequency (TF) domain, and each observed signal is uniquely clustered into its corresponding subspace. The estimation of source signals is calculated using the inverse or pseudo-inverse matrix of the mixing matrix. Mathematical and experimental results demonstrate the promising potential of the proposed subspace clustering method to solve the dependent BSS (DBSS) problems under relaxed sparsity conditions.
IEEE SIGNAL PROCESSING LETTERS
(2023)
Article
Computer Science, Artificial Intelligence
Guang Hua, Andrew Beng Jin Teoh, Yong Xiang, Hao Jiang
Summary: The unprecedented success of deep learning relies on the synergy of big data, computing power, and human knowledge. Copyright protection of deep neural networks (DNNs) is necessary, and DNN watermarking is a popular solution for this.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Stella Ho, Ming Liu, Lan Du, Longxiang Gao, Yong Xiang
Summary: Continual learning is a machine learning paradigm that learns continuously without forgetting previously acquired knowledge. Existing models often save old examples and revisit previously seen data to retain old knowledge, but the occupied memory size keeps growing. Therefore, we propose a memory-efficient method that stores a few samples to achieve good performance.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Information Systems
Jie Li, Yong Xiang, Hao Wu, Shaowen Yao, Dan Xu
Summary: The study introduced a novel patch-based style transfer method that operates directly in the image pixel domain without using neural networks, achieving fascinating style transfer results with rich image details.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)
Article
Computer Science, Information Systems
Yaxi Yang, Yao Tong, Jian Weng, Yufeng Yi, Yandong Zheng, Leo Yu Zhang, Rongxing Lu
Summary: This article presents a query scheme for privacy-preserving on genomic data, which allows secure querying of specific ranges of genomic data in a database.
IEEE TRANSACTIONS ON CLOUD COMPUTING
(2023)
Article
Computer Science, Information Systems
Xia Liang, Jie Guo, Peide Liu
Summary: This paper investigates a novel consensus model based on social networks to manage manipulative and overconfident behaviors in large-scale group decision-making. By proposing a novel clustering model and improved methods, the consensus reaching is effectively facilitated. The feedback mechanism and management approach are employed to handle decision makers' behaviors. Simulation experiments and comparative analysis demonstrate the effectiveness of the model.
INFORMATION SCIENCES
(2024)
Article
Computer Science, Information Systems
Xiang Li, Haiwang Guo, Xinyang Deng, Wen Jiang
Summary: This paper proposes a method based on class gradient networks for generating high-quality adversarial samples. By introducing a high-level class gradient matrix and combining classification loss and perturbation loss, the method demonstrates superiority in the transferability of adversarial samples on targeted attacks.
INFORMATION SCIENCES
(2024)
Article
Computer Science, Information Systems
Lingyun Lu, Bang Wang, Zizhuo Zhang, Shenghao Liu
Summary: Many recommendation algorithms only rely on implicit feedbacks due to privacy concerns. However, the encoding of interaction types is often ignored. This paper proposes a relation-aware neural model that classifies implicit feedbacks by encoding edges, thereby enhancing recommendation performance.
INFORMATION SCIENCES
(2024)
Article
Computer Science, Information Systems
Jaehong Yu, Hyungrok Do
Summary: This study discusses unsupervised anomaly detection using one-class classification, which determines whether a new instance belongs to the target class by constructing a decision boundary. The proposed method uses a proximity-based density description and a regularized reconstruction algorithm to overcome the limitations of existing one-class classification methods. Experimental results demonstrate the superior performance of the proposed algorithm.
INFORMATION SCIENCES
(2024)
Article
Computer Science, Information Systems
Hui Tu, Shifei Ding, Xiao Xu, Haiwei Hou, Chao Li, Ling Ding
Summary: Border-Peeling algorithm is a density-based clustering algorithm, but its complexity and issues on unbalanced datasets restrict its application. This paper proposes a non-iterative border-peeling clustering algorithm, which improves the clustering performance by distinguishing and associating core points and border points.
INFORMATION SCIENCES
(2024)
Article
Computer Science, Information Systems
Long Tang, Pan Zhao, Zhigeng Pan, Xingxing Duan, Panos M. Pardalos
Summary: In this work, a two-stage denoising framework (TSDF) is proposed for zero-shot learning (ZSL) to address the issue of noisy labels. The framework includes a tailored loss function to remove suspected noisy-label instances and a ramp-style loss function to reduce the negative impact of remaining noisy labels. In addition, a dynamic screening strategy (DSS) is developed to efficiently handle the nonconvexity of the ramp-style loss.
INFORMATION SCIENCES
(2024)
Article
Computer Science, Information Systems
Raghunathan Krishankumar, Sundararajan Dhruva, Kattur S. Ravichandran, Samarjit Kar
Summary: Health 4.0 is gaining global attention for better healthcare through digital technologies. This study proposes a new decision-making framework for selecting viable blockchain service providers in the Internet of Medical Things (IoMT). The framework addresses the limitations in previous studies and demonstrates its applicability in the Indian healthcare sector. The results show the top ranking BSPs, the importance of various criteria, and the effectiveness of the developed model.
INFORMATION SCIENCES
(2024)
Article
Computer Science, Information Systems
Tao Tan, Hong Xie, Liang Feng
Summary: This paper proposes a heterogeneous update idea and designs HetUp Q-learning algorithm to enlarge the normalized gap by overestimating the Q-value corresponding to the optimal action and underestimating the Q-value corresponding to the other actions. To address the limitation, a softmax strategy is applied to estimate the optimal action, resulting in HetUpSoft Q-learning and HetUpSoft DQN. Extensive experimental results show significant improvements over SOTA baselines.
INFORMATION SCIENCES
(2024)
Article
Computer Science, Information Systems
Chao Yang, Xianzhi Wang, Lina Yao, Guodong Long, Guandong Xu
Summary: This paper proposes a dynamic transformer-based architecture called Dyformer for multivariate time series classification. Dyformer captures multi-scale features through hierarchical pooling and adaptive learning strategies, and improves model performance by introducing feature-map-wise attention mechanisms and a joint loss function.
INFORMATION SCIENCES
(2024)
Article
Computer Science, Information Systems
Xiguang Li, Baolu Feng, Yunhe Sun, Ammar Hawbani, Saeed Hammod Alsamhi, Liang Zhao
Summary: This paper proposes an enhanced scatter search strategy, using opposition-based learning, to solve the problem of automated test case generation based on path coverage (ATCG-PC). The proposed ESSENT algorithm selects the path with the lowest path entropy among the uncovered paths as the target path and generates new test cases to cover the target path by modifying the dimensions of existing test cases. Experimental results show that the ESSENT algorithm outperforms other state-of-the-art algorithms, achieving maximum path coverage with fewer test cases.
INFORMATION SCIENCES
(2024)
Article
Computer Science, Information Systems
Shirin Dabbaghi Varnosfaderani, Piotr Kasprzak, Aytaj Badirova, Ralph Krimmel, Christof Pohl, Ramin Yahyapour
Summary: Linking digital accounts belonging to the same user is crucial for security, user satisfaction, and next-generation service development. However, research on account linkage is mainly focused on social networks, and there is a lack of studies in other domains. To address this, we propose SmartSSO, a framework that automates the account linkage process by analyzing user routines and behavior during login processes. Our experiments on a large dataset show that SmartSSO achieves over 98% accuracy in hit-precision.
INFORMATION SCIENCES
(2024)
Article
Computer Science, Information Systems
Renchao Wu, Jianjun He, Xin Li, Zuguo Chen
Summary: This paper proposes a memetic algorithm with fuzzy-based population control (MA-FPC) to solve the joint order batching and picker routing problem (JOBPRP). The algorithm incorporates batch exchange crossover and a two-level local improvement procedure. Experimental results show that MA-FPC outperforms existing algorithms in terms of solution quality.
INFORMATION SCIENCES
(2024)
Article
Computer Science, Information Systems
Guoxiang Zhong, Fagui Liu, Jun Jiang, Bin Wang, C. L. Philip Chen
Summary: In this study, we propose the AMFormer framework to address the problem of mixed normal and anomaly samples in deep unsupervised time-series anomaly detection. By refining the one-class representation and introducing the masked operation mechanism and cost sensitive learning theory, our approach significantly improves anomaly detection performance.
INFORMATION SCIENCES
(2024)
Article
Computer Science, Information Systems
Jin Zhou, Kang Zhou, Gexiang Zhang, Ferrante Neri, Wangyang Shen, Weiping Jin
Summary: In this paper, the authors focus on the issue of multi-objective optimisation problems with redundant variables and indefinite objective functions (MOPRVIF) in practical problem-solving. They propose a dual data-driven method for solving this problem, which consists of eliminating redundant variables, constructing objective functions, selecting evolution operators, and using a multi-objective evolutionary algorithm. The experiments conducted on two different problem domains demonstrate the effectiveness, practicality, and scalability of the proposed method.
INFORMATION SCIENCES
(2024)
Article
Computer Science, Information Systems
Georgios Charizanos, Haydar Demirhan, Duygu Icen
Summary: This article proposes a new fuzzy logistic regression framework that addresses the problems of separation and imbalance while maintaining the interpretability of classical logistic regression. By fuzzifying binary variables and classifying subjects based on a fuzzy threshold, the framework demonstrates superior performance on imbalanced datasets.
INFORMATION SCIENCES
(2024)