通讯机构:
[Xiangling Ding] S;School of Computer and Communication Engineering, Hunan University of Science and Technology, Xiangtan, China<&wdkj&>State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China<&wdkj&>Guangdong Provincial Key Laboratory of Information Security Technology, Guangzhou, China
关键词:
Deepfakes;CNN;Spatial domain;Residual domain
摘要:
With the rapid development of Internet technology, the Internet is full of false information, and Deepfakes, as a kind of visual forgery content, brings the greatest impact to people. The existing mainstream Deepfakes public datasets often have millions of frames, and if the first N frames are used to train the model some key features may be lost. If all frames are used, the model is easily overfitted and training often takes several days, which greatly consumes computational resources. Therefore, we propose an adaptive video frame extraction algorithm to extract the required number of frames from all video frames. The algorithm is able to reduce data redundancy and increase feature richness. In addition, we design a two-stream Deepfakes detection network SRTNet by combining the image spatial domain and residual domain, which consists of spatial-stream and residual-stream. The spatial-stream uses the original RGB image as input to capture high-level tampering artifacts. Residual-stream uses three sets of high-pass filters to process the input image to obtain the image residuals to capture the tampering traces. Two-stream parallel training, and the features are concatenated to enable the model to capture tamper features from both spatial and residual domains to achieve better detection performance. The experimental results show that the proposed adaptive frame extraction algorithm can improve the model performance. And the proposed detection network SRTNet achieves better results than previous work on mainstream Deepfake dataset.
作者机构:
[Kuang L.-D.; Gui Y.; Li W.] School of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha, 410114, China
会议名称:
29th International Conference on Neural Information Processing, ICONIP 2022
作者机构:
[Sun, Cheng] Hunan Normal Univ, Sch Math & Stat, Changsha 410081, Peoples R China.;[Wu, Xingjin; Zhang, Jin; Wen, Pei; Zhang, Shiwen] Hunan Normal Univ, Coll Informat Sci & Engn, Changsha 410081, Peoples R China.;[Zhang, Jin] Changsha Univ Sci & Technol, Sch Comp & Commun Engn, Changsha 410114, Peoples R China.;[Gong, Hongfang] Changsha Univ Sci & Technol, Sch Math & Stat, Changsha 410114, Peoples R China.
通讯机构:
[Jin Zhang] C;College of Information Science and Engineering, Hunan Normal University, Changsha 410081, China<&wdkj&>School of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha 410114, China<&wdkj&>Author to whom correspondence should be addressed.
关键词:
face detection;adaptive fusion;Classroom-Face
摘要:
Face detection in the classroom environment is the basis for student face recognition, sensorless attendance, and concentration analysis. Due to equipment, lighting, and the uncontrollability of students in an unconstrained environment, images include many moving faces, occluded faces, and extremely small faces in a classroom environment. Since the image sent to the detector will be resized to a smaller size, the face information extracted by the detector is very limited. This seriously affects the accuracy of face detection. Therefore, this paper proposes an adaptive fusion-based YOLOv5 method for face detection in classroom environments. First, a very small face detection layer in YOLOv5 is added to enhance the YOLOv5 baseline, and an adaptive fusion backbone network based on multi-scale features is proposed, which has the ability to feature fusion and rich feature information. Second, the adaptive spatial feature fusion strategy is applied to the network, considering the face location information and semantic information. Finally, a face dataset Classroom-Face in the classroom environment is creatively proposed, and it is verified with our method. The experimental results show that, compared with YOLOv5 or other traditional algorithms, our algorithm portrays better performance in WIDER-FACE Dataset and Classroom-Face dataset.
摘要:
Generally, the computational grid consists of a large number of computing nodes, some of them are idle due to the uneven geographical distribution of computing requirements. This may cause workload unbalancing problems, which affect the performance of large-scale computational grids. In order to balance the computing requirements and computing nodes, we propose a job scheduling algorithm based on the workload prediction of computing nodes. We first analyze the causes of workload imbalance and the feasibility of reallocating computing resources. Secondly, we design an application and workload -aware scheduling algorithm (AWAS) by combining the previously designed workload prediction model. To reduce the complexity of the AWAS algorithm, we propose a parallel job scheduling method based on computing node workload prediction. The experiments show that the AWAS algorithm can balance the workload among different computing nodes on the real-world dataset. In addition, we propose the parallelism of workload prediction model from the perspective of internal structure and data set to make AWAS apply to more computing nodes of the large-scale computing grids. Experimental results show that the combination of the two can achieve satisfactory acceleration efficiency.(c) 2022 Elsevier Inc. All rights reserved.
期刊:
Information Sciences,2023年644:119220 ISSN:0020-0255
通讯作者:
Xiong, NN
作者机构:
[Guo, Meng; He, Shiming; Lei, Ying; Li, Zhuozhou; Zhou, Siyuan] Changsha Univ Sci & Technol, Sch Comp & Commun Engn, Hunan Prov Key Lab Intelligent Proc Big Data Tran, Key Lab Safety Control Bridge Engn,Minist Educ, Changsha 410114, Hunan, Peoples R China.;[Xie, Kun] Hunan Univ, Coll Comp Sci & Elect Engn, Changsha 410082, Hunan, Peoples R China.;[Xiong, Neal N.; Xiong, NN] Ross State Univ, Dept Comp Math & Phys Sci, Alpine, TX 79830 USA.
通讯机构:
[Xiong, NN ] R;Ross State Univ, Dept Comp Math & Phys Sci, Alpine, TX 79830 USA.
关键词:
Time series clustering;Irregular sampling;Matrix factorization;Iteration
摘要:
Key Performance Indicator (KPI) clustering plays an important role in Artificial Intelligence for IT Operations (AIOps) when the number of KPIs is large. This approach can effectively reduce the overhead by dividing KPIs into several classes, then applying the same anomaly detection or prediction model to all KPIs in a class. However, KPI sampling strategies vary depending on the environment in question, which leads to the production of irregular KPIs. Few existing works have considered the clustering of KPIs with irregular sampling. Matrix factorization (MF) is widely applied in low-rank data recovery and can be used to align and fill irregular KPIs. However, the clustering performance after recovering and filling by MF remains unknown. These two problems interact with each other and should therefore be solved together. Accordingly, we formulate the joint MF and clustering problem for irregular KPIs and design an iterative clustering scheme based on MF. This iterative clustering scheme comprises alignment and pre-filling, the loop of clustering, and subclass filling by MF, and can work with two pre-filling methods. Extensive experiments on two real-world datasets show that the iterative clustering scheme can obtain higher normalized mutual information (NMI) than non-iterative clustering, while also consuming less computational time than Dynamic Time Warping (DTW). The two kinds of pre-filling methods each have their advantages on different datasets.
作者机构:
[Zhao, Wei; Wang, Fu-qiang] Qilu Univ Technol, Shandong Acad Sci, Shandong Comp Sci Ctr, Natl Supercomp Ctr Jinan,Key Lab Comp Power Networ, Jinan, Peoples R China.;[Zhao, Wei; Wang, Fu-qiang] Shandong Fundamental Res Ctr Comp Sci, Shandong Prov Key Lab Comp Networks, Jinan, Peoples R China.;[Mao, Yi-yu; Zhong, Hai] Changsha Univ Sci & Technol, Sch Comp & Commun Engn, Changsha 410015, Peoples R China.;[Ding, Chao] Hunan Univ, Coll Elect & Informat Engn, Changsha 410082, Peoples R China.;[Ruan, XC; Ruan, Xin-chao] Cent South Univ, Sch Automat, Changsha 410083, Peoples R China.
通讯机构:
[Ruan, XC ] C;Cent South Univ, Sch Automat, Changsha 410083, Peoples R China.
关键词:
Quantum teleportation;Continuous-variable;Quantum digital signature
摘要:
In this paper, a continuous-variable quantum digital signature (CV-QDS) protocol based on quantum telepor-tation (QT) is proposed, and the corresponding theoretical analysis method is established. Unlike previous schemes, we use squeezed states to carry key and secret information about the teleported states that are transmitted through classical and entangled channels without infinite squeezing. In addition, for multibit information signatures, we propose to use the mean and modulation variance of the teleported quantum state to distinguish signatures, and each of which is marked and ordered. In particular, we derive the fidelity that the protocol can achieve, displaying the effectiveness of the method at different compression levels. Security analysis demonstrates that the protocol possesses unforgeability, non-repudiation and robustness, which is suitable for signing one-bit and multibit messages.
摘要:
Siamese trackers have achieved significant progress over the past few years. However, the existing methods are either high speed or high performance, and it is difficult for previous Siamese trackers to balance both. In this work, we propose a high-performance yet effective tracker (SiamSERPN), which utilizes MobileNetV2 as the backbone and equips with the proposed squeeze and excitation region proposal network (SERPN). For the SERPN block, we introduce the distance-IoU (DIoU) into the classification and regression branches to remedy the weakness of traditional RPN. Benefiting from the structure of MobileNetV2, we propose a feature aggregation architecture of multi-SERPN blocks to improve performance further. Extensive experiments and comparisons on visual tracking benchmarks, including VOT2016, VOT2018, and GOT-10k, demonstrate that our SiamSERPN can balance speed and performance. Especially on GOT-10k benchmark, our tracker scores 0.604 while running at 75 frames per second (FPS), which is nearly 27 times that of the state-of-the-art tracker.
期刊:
ACM Transactions on Internet Technology,2023年23(3):1–23 ISSN:1533-5399
作者机构:
[Wang, Jin] School of Computer Science and Mathematics, Fujian University of Technology;School of Computer & Communication Engineering, Changsha University of Science & Technology, China;[Chen, Jiahao] School of Computer Science and Mathematics, Fujian University of Technology, China;[Ren, Yongjun] School of Computer and Software, Nanjing University of Information Science & Technology, China;[Xiong, Neal] Department of Computer Science and Mathematics, Sul Ross State University, USA
关键词:
Blockchainzero-trustInternet of Thingsdate storagecryptographic commitment
摘要:
With the development of the Internet of Things (IoT), a large-scale, heterogeneous, and dynamic distributed network has been formed among IoT devices. There is an extreme need to establish a trust mechanism between devices, and blockchain can provide a zero-trust security framework for IoT. However, the efficiency of the blockchain is far from meeting the application requirements of the IoT, which has become the biggest resistance to the application of the blockchain in the IoT. Therefore, this paper combines sharding to build an effective Blockchain-based IoT data storage scheme (S-BDS). Sharding can solve the problem of blockchain capacity and scalability. While the blockchain provides data immutability and traceability for the IoT, it also brings huge demands for data credibility verification. The communication delay in the IoT system seriously affects the security of the system, while the Merkle proof of traditional blockchain occupies a lot of communication resources. This paper constructs Insertable Vector Commitment (IVC) in the bilinear group and replaces the Merkle tree with IVC to store IoT data in the blockchain. The construct has small-sized proof. It also has the ability to record the number of updates, which can prevent replay-attacks. Experiments show that each block processes 1,000 transactions, the proof size of a single data piece is 30% of the original scheme, and proofs from different shards can be aggregated. IVC can effectively reduce communication congestion and improve the stability and security of the IoT system. With the development of the Internet of Things (IoT), a large-scale, heterogeneous, and dynamic distributed network has been formed among IoT devices. There is an extreme need to establish a trust mechanism between devices, and blockchain can provide a zero-trust security framework for IoT. However, the efficiency of the blockchain is far from meeting the application requirements of the IoT, which has become the biggest resistance to the application of the blockchain in the IoT. Therefore, this paper combines sharding to build an effective Blockchain-based IoT data storage scheme (S-BDS). Sharding can solve the problem of blockchain capacity and scalability. While the blockchain provides data immutability and traceability for the IoT, it also brings huge demands for data credibility verification. The communication delay in the IoT system seriously affects the security of the system, while the Merkle proof of traditional blockchain occupies a lot of communication resources. This paper constructs Insertable Vector Commitment (IVC) in the bilinear group and replaces the Merkle tree with IVC to store IoT data in the blockchain. The construct has small-sized proof. It also has the ability to record the number of updates, which can prevent replay-attacks. Experiments show that each block processes 1,000 transactions, the proof size of a single data piece is 30% of the original scheme, and proofs from different shards can be aggregated. IVC can effectively reduce communication congestion and improve the stability and security of the IoT system.
通讯机构:
[Chunhua Wang] C;College of Computer Science and Electronic Engineering, Hunan University, Changsha 410082, China<&wdkj&>Author to whom correspondence should be addressed.
关键词:
artificial fish swarm algorithm;hyper-chaotic system;image encryption;DNA
摘要:
Aiming at the problems of small key space and weak resistance to differential attacks in existing encryption algorithms, we proposed a chaotic digital image encryption scheme based on an optimized artificial fish swarm algorithm and DNA coding. First, the key is associated with the ordinary image pixel through the MD5 hash operation, and the hash value generated by the ordinary image is used as the initial value of the hyper-chaotic system to increase the sensitivity of the key. Next, the artificial fish school algorithm is used to scramble the positions of pixels in the block. In addition, scrambling operation between blocks is proposed to increase the scrambling effect. In the diffusion stage, operations are performed based on DNA encoding, obfuscation, and decoding technologies to obtain encrypted images. The research results show that the optimized artificial fish swarm algorithm has good convergence and can obtain the global optimal solution to the greatest extent. In addition, simulation experiments and security analysis show that compared with other encryption schemes, the scheme proposed in this paper has a larger key space and better resistance to differential attacks, indicating that the proposed algorithm has better encryption performance and higher security.
通讯机构:
[Chunhua Wang] C;College of Computer Science and Electronic Engineering, Hunan University, Changsha 410082, China<&wdkj&>Author to whom correspondence should be addressed.
摘要:
Since the Lorenz chaotic system was discovered in 1963, the construction of chaotic systems with complex dynamics has been a research hotspot in the field of chaos. Recently, memristive Hopfield neural networks (MHNNs) offer great potential in the design of complex, chaotic systems because of their special network structures, hyperbolic tangent activation function, and memory property. Many chaotic systems based on MHNNs have been proposed and exhibit various complex dynamical behaviors, including hyperchaos, coexisting attractors, multistability, extreme multistability, multi-scroll attractors, multi-structure attractors, and initial-offset coexisting behaviors. A comprehensive review of the MHNN-based chaotic systems has become an urgent requirement. In this review, we first briefly introduce the basic knowledge of the Hopfiled neural network, memristor, and chaotic dynamics. Then, different modeling methods of the MHNN-based chaotic systems are analyzed and discussed. Concurrently, the pioneering works and some recent important papers related to MHNN-based chaotic systems are reviewed in detail. Finally, we survey the progress of MHNN-based chaotic systems for application in various scenarios. Some open problems and visions for the future in this field are presented. We attempt to provide a reference and a resource for both chaos researchers and those outside the field who hope to apply chaotic systems in a particular application.
作者机构:
[Li, Jia] Hunan Ind Polytech, Sch Informat Engn, Changsha 410036, Peoples R China.;[Li, Wenjun; Yang, Xueying] Changsha Univ Sci & Technol, Sch Comp & Commun Engn, Hunan Prov Key Lab Intelligent Proc Big Data Trans, Changsha 410015, Peoples R China.;[Yang, Yongjie] Saarland Univ, Chair Econ Theory, D-66123 Saarbrucken, Germany.
通讯机构:
[Xueying Yang] H;Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation, School of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha, China
通讯机构:
[Fei Yu] S;School of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha 410114, China<&wdkj&>Author to whom correspondence should be addressed.
摘要:
In this paper, we first present a simple seven-term 4D hyperchaotic system based on the classical Sprott-C 3D chaotic system. This novel system is inspired by the simple 4D hyperchaotic system based on Sprott-B proposed by A. T. Sheet (2022). We discuss the phenomenon of premature divergence brought about by the improper choice of coupling parameters in that paper and describe the basic properties of the new system with phase diagrams, Lyapunov exponential spectra and bifurcation diagrams. Then, we find that the dynamical behaviors of the system suffer from the limitation of the control parameters and cannot represent the process of motion in detail. To improve the system, we expand the dimensionality and add the control parameters and memristors. A 5D memristive hyperchaotic system with hidden attractors is proposed, and the basic dynamical properties of the system, such as its dissipation, equilibrium point, stability, Lyapunov exponential spectra and bifurcation diagram, are analyzed. Finally, the hardware circuits of the 4D Sprott-C system and the 5D memristive hyperchaotic system were realized by a field programmable gate array (FPGA) and verified by an experiment. The experimental results are consistent with the numerical simulation results obtained in MATLAB, which demonstrates the feasibility and potential of the system.
通讯机构:
[Yin, B ] C;ChangSha Univ Sci & Technol, Sch Comp & Commun Engn, Changsha 410114, Peoples R China.
关键词:
Crowdsourcing systems;Task assignment;Proxies;Quality control
摘要:
Traditional task assignment follows a direct recruitment model in which requesters recruit and select workers to complete tasks. Because of the unclear division of roles and the diversity of each role’s mission, this model is neither efficient nor scalable. This paper introduces the concept of cooperative unit (CU), in which workers are organized into cooperative units, whose proxies bid for tasks from requesters based on worker characteristics. However, because of the decentralization of task assignment, quality control is complicated, and the benefits of different roles must be balanced. As a result, we propose a novel two-tier task assignment framework (TTAF) that produces high-quality results while striking the appropriate balance between requesters, CUs, and workers. We first propose a vector-based expertise representation model that evaluates workers’ expertise based on previous answers. Then, we devise a higher-tier task assignment between tasks and CUs that maximizes answer quality while staying within budget. The quality of the answers is ensured by aspects such as keyword coverage, overall expertise, and the number of workers. We also devise lower-tier task assignment, which evenly distributes tasks among workers such that more workers have the opportunity to perform tasks. The extensive evaluation shows that our proposed approaches achieve promising results.
作者:
Wang J.;Lei X.;Jiang Q.;Alfarraj O.;Tolba A.;...
期刊:
Computer Systems Science and Engineering,2023年45(2):1727-1742 ISSN:0267-6192
通讯作者:
Kim, G.-J.
作者机构:
[Jiang Q.; Wang J.; Lei X.] School of Computer & Communication Engineering, Changsha University of Science & Technology, Changsha, 410114, China;[Tolba A.; Alfarraj O.] Computer Science Department, Community College, King Saud University, Riyadh, 11437, Saudi Arabia;[Kim G.-J.] Department of Computer Engineering, Chonnam National University, Gwangju, 61186, South Korea
通讯机构:
[Kim, G.-J.] D;Department of Computer Engineering, South Korea
关键词:
deep factorization machine;denial-of-service attacks;GRMMP;Software-defined network