检索结果-内蒙古大学图书馆

AccUDNN: A GPU Memory Efficient Accelerator for Training Ultra-Deep Neural Networks

学校读者我要写书评

暂无评论

AccUDNN: A GPU Memory Efficient Accelerator for Training Ult...

IEEE International Conference on computer Design: VLSI in computers and Processors, (ICCD)

作者： Jinrong Guo Wantao Liu Wang Wang Chunrong Yao Jizhong Han Ruixuan Li Yijun Lu Songlin Hu Chinese Academy of Sciences Institute of Information Engineering School of Cyber Security University of Chinese Academy of Sciences School of Computer Science and Engineering Nanjing University of Science and Technology Alibaba Cloud Computing Co. Ltd. Beijing China

With the implementation of mainstream DL frameworks, scarce GPU memory resource is the primary bottleneck that hinders the trainability and training efficiency of ultra-deep neural networks (UDNN). Prior memory optimization works focus on removing the trainability restriction but leave the training efficiency out of consideration. To fill the gap, we present "AccUDNN", an accelerator that aims to make full use of finite GPU memory resource to speed up the training process of UDNN in this paper. AccUDNN mainly includes two modules: memory optimizer and hyperparameter tuner. Memory optimizer develops a novel performance-model guided dynamic swap out/in strategy to meet trainability first and further remedy the efficiency degradation in other swapping strategies. Then, a hyperparameter tuner is designed to explore the efficiency-optimal minibatch size and the matched learning rate after applying the dynamic swapping strategy. Evaluations demonstrate that AccUDNN cuts down the GPU memory requirement of ResNet-152 from more than 24GB to 8GB. In turn, given 12GB GPU memory budget, the efficiency-optimal minibatch size can reach 4.2x larger than Caffe and finally improve the scaling efficiency (speedup) of 8 GPUs' cluster by 1.9x.

关键词：

An energy efficient authentication scheme using chebyshev chaotic map for smart grid environment

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhang, Liping Zhu, Yue Ren, Wei Wang, Yinghan Xiong, Neal N. Zhang, Yan School of Computer Science China University of Geosciences Wuhan430074 China School of Computer Science China University of Geosciences Guangxi Key Laboratory of Cryptography and Information Security Guilin541004 China Key Laboratory of Network Assessment Technology CAS [Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China Department of Mathematics and Computer Science Northeastern State University OK74464 United States Department of Informatics University of Oslo Norway

Smart grid (SG) is an automatic electric power transmission network with bidirectional flows of both energy and information. As one of the important applications of smart grid, charging between electric vehicles has attracted much attentions. However, authentication between vehicle users and an aggregator may be vulnerable to various attacks due to the usage of wireless communications. Although several authentication schemes are proposed for smart grid environments with privacy protection, some of them still impose security issues such as anonymity absence. In addition, most of the existing authentication schemes have not thoroughly tackled the charging peak in their design, so these schemes cannot guarantee the requirement in terms of low energy consumption in smart grid environments. In order to reduce the computational costs yet preserve required security, the Chevyshev chaotic map based authentication schemes are proposed. However, the security requirements of Chebyshev polynomials bring a new challenge to the design of authentication schemes based on Chebyshev chaotic maps. To solve this issue, we propose a practical Chebyshev polynomial algorithm by using a binary exponentiation algorithm based on square matrix to achieve secure and efficient Chebyshev polynomial computation. We further apply the proposed algorithm to construct an energy-efficient authentication and key agreement scheme for smart grid environments. Compared with state-of-the-art schemes, the proposed authentication scheme effectively reduces the computational costs and communication costs by adopting the proposed Chebyshev polynomial algorithm. Furthermore, the ProVerif tool is employed to analyze the security of the proposed authentication scheme. Our experimental results justified that our proposed authentication scheme can outperform state-of-the-art schemes in terms of the computational overhead while achieving privacy protection. Copyright © 2020, The Authors. All rights reserved.

关键词： Authentication

Multi-Parameter Performance Modeling Based on Machine Learning with Basic Block Features

学校读者我要写书评

暂无评论

Multi-Parameter Performance Modeling Based on Machine Learni...

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Meng Hao Weizhe Zhang Yiming Wang Dong Li Wen Xia Hao Wang Chen Lou School of Computer Science and Technology Harbin Institute of Technology China Cyberspace Security Research Center Peng Cheng Laboratory Shenzhen China Department of Electrical Engineering and Computer Science University of California Merced Department of Computer Science Norwegian University of Science and Technology Norway

ISBN: (数字)9781728143286

ISBN: (纸本)9781728143293

Considering the increasing complexity and scale of HPC architecture and software, the performance modeling of parallel applications on large-scale HPC platforms has become increasingly important. It plays an important role in many areas, such as performance analysis, job management, and resource estimation. In this work, we propose a multi-parameter performance modeling and prediction framework called MPerfPred, which utilizes basic block frequencies as features and uses machine learning algorithms to automatically construct multi-parameter performance models with high generalization ability. To reduce the prediction overhead, we propose some feature-filtering strategies to reduce the number of features in the training stage and build a serial program called BBF collector for each target application to quickly collect feature values in the prediction stage. We demonstrate the use of MPerfPred on the TianHe-2 supercomputer with six parallel applications. Results show that MPerfPred with SVR achieves better prediction than other input parameter-based modeling methods. The average prediction error and average standard deviation of prediction errors of MPerfPred are 8.42% and 6.09%, respectively. In the prediction stage, the average prediction overhead of MPerfPred is less than 0.13% of the total execution time.

关键词： Training Predictive models Machine learning algorithms Machine learning Instruments Data models Prediction algorithms

Ensuring data confidentiality via plausibly deniable encryption and secure deletion-a survey

学校读者我要写书评

暂无评论

cybersecurity 2018年第1期1卷 106-125页

作者： Qionglu Zhang Shijie Jia Bing Chang Bo Chen Data Assurance and Communication Security Research Center Chinese Academy of SciencesBeijingChina State Key Laboratory of Information Security Institute of Information EngineeringChinese Academy of SciencesBeijingChina School of Cyber Security University of Chinese Academy of SciencesBeijingChina School of Information Systems Singapore Management UniversitySingaporeSingapore Department of Computer Science Michigan Technological UniversityHoughtonUSA

Ensuring confidentiality of sensitive data is of paramount importance,since data leakage may not only endanger data owners’privacy,but also ruin reputation of businesses as well as violate various regulations like HIPPA and Sarbanes-Oxley *** provide confidentiality guarantee,the data should be protected when they are preserved in the personal computing devices(i.e.,confidentiality during their lifetime);and also,they should be rendered irrecoverable after they are removed from the devices(i.e.,confidentiality after their lifetime).Encryption and secure deletion are used to ensure data confidentiality during and after their lifetime,*** work aims to perform a thorough literature review on the techniques being used to protect confidentiality of the data in personal computing devices,including both encryption and secure *** for encryption,we mainly focus on the novel plausibly deniable encryption(PDE),which can ensure data confidentiality against both a coercive(i.e.,the attacker can coerce the data owner for the decryption key)and a non-coercive attacker.

关键词： Data confidentiality Plausibly deniable encryption Secure deletion

Covid-19 public opinion and emotion monitoring system based on time series thermal new word mining

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhang, Yixian Chen, Jieren Liu, Boyi Yang, Yifan Li, Haocheng Zheng, Xinyi Chen, Xi Ren, Tenglong Xiong, Naixue School of Information and Communication Engineering Hainan University Haikou570100 China School of Computer Science and Cyberspace Security Hainan University Haikou570100 China University of Chinese Academy of Sciences Shenzhen518000 China National University of Defense Technology Changsha410000 China Department of Mathematics and Computer Science Northeastern State University TahlequahOK United States

With the spread and development of new epidemics, it is of great reference value to identify the changing trends of epidemics in public emotions. We designed and implemented the COVID-19 public opinion monitoring system based on time series thermal new word mining. A new word structure discovery scheme based on the timing explosion of network topics and a Chinese sentiment analysis method for the COVID-19 public opinion environment are proposed. Establish a "Scrapy-Redis-Bloomfilter" distributed crawler framework to collect data. The system can judge the positive and negative emotions of the reviewer based on the comments, and can also reflect the depth of the seven emotions such as Hopeful, Happy, and Depressed. Finally, we improved the sentiment discriminant model of this system and compared the sentiment discriminant error of COVID-19 related comments with the Jiagu deep learning model. The results show that our model has better generalization ability and smaller discriminant error. We designed a large data visualization screen, which can clearly show the trend of public emotions, the proportion of various emotion categories, keywords, hot topics, etc., and fully and intuitively reflect the development of public opinion. Copyright © 2020, The Authors. All rights reserved.

关键词： Monitoring

RRNet: Relational reasoning network with parallel multi-scale attention for salient object detection in optical remote sensing images

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Cong, Runmin Zhang, Yumo Fang, Leyuan Li, Jun Zhang, Chunjie Zhao, Yao Kwong, Sam Institute of Information Science Beijing Jiaotong University Beijing100044 China Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China Department of Computer Science City University of Hong Kong Hong Kong College of Electrical and Information Engineering Hunan University Changsha410082 China Peng Cheng Laboratory Shenzhen518000 China Guangdong Provincial Key Laboratory of Urbanization and Geosimulation School of Geography and Planning Sun Yat-sen University Guangzhou510275 China Key Laboratory of Information Perception and Systems for Public Security of MIIT Nanjing University of Science and Technology Nanjing210094 China Department of Computer Science City University of Hong Kong Hong Kong City University of Hong Kong Shenzhen Research Institute Shenzhen51800 China

Salient object detection (SOD) for optical remote sensing images (RSIs) aims at locating and extracting visually distinctive objects/regions from the optical RSIs. Despite some saliency models were proposed to solve the intrinsic problem of optical RSIs (such as complex background and scale-variant objects), the accuracy and completeness are still unsatisfactory. To this end, we propose a relational reasoning network with parallel multi-scale attention for SOD in optical RSIs in this paper. The relational reasoning module that integrates the spatial and the channel dimensions is designed to infer the semantic relationship by utilizing high-level encoder features, thereby promoting the generation of more complete detection results. The parallel multi-scale attention module is proposed to effectively restore the detail information and address the scale variation of salient objects by using the low-level features refined by multi-scale attention. Extensive experiments on two datasets demonstrate that our proposed RRNet outperforms the existing state-of-the-art SOD competitors both qualitatively and quantitatively. https://***/proj_***. © 2021, CC BY-NC-SA.

关键词： Object detection

Beam-Domain Secret Key Generation for Multi-User Massive MIMO Networks

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Chen, You Li, Guyue Sun, Chen Zhang, Junqing Jorswieck, Eduard Xiao, Bin School of Cyber Science and Engineering Southeast University Nanjing210096 China National Mobile Communications Research Laboratory Southeast University Nanjing210096 China Purple Mountain Laboratories for Network and Communication Security Nanjing210096 China Department of Electrical Engineering and Electronics University of Liverpool LiverpoolL69 3GJ United Kingdom Institute for Communications Technology Technische Universität Braunschweig Germany Department of Computing Hong Kong Polytechnic University Hong Kong

Physical-layer key generation (PKG) in multi-user massive MIMO networks faces great challenges due to the large length of pilots and the high dimension of channel matrix. To tackle these problems, we propose a novel massive MIMO key generation scheme with pilot reuse based on the beam domain channel model and derive close-form expression of secret key rate. Specifically, we present two algorithms, i.e., beam-domain based channel probing (BCP) algorithm and interference neutralization based multi-user beam allocation (IMBA) algorithm for the purpose of channel dimension reduction and multi-user pilot reuse, respectively. Numerical results verify that the proposed PKG scheme can achieve the secret key rate that approximates the perfect case, and significantly reduce the dimension of the channel estimation and pilot overhead. Copyright © 2020, The Authors. All rights reserved.

关键词： Cryptography

Distortion-free watermarking scheme for compressed data in columnar database 15

学校读者我要写书评

暂无评论

Distortion-free watermarking scheme for compressed data in c...

15th International Joint Conference on e-Business and Telecommunications, ICETE 2018

作者： Yaqub, Waheeb Kamel, Ibrahim Aung, Zeyar Center for Cyber Security New York University Abu Dhabi United Arab Emirates Department of Electrical and Computer Engineering University of Sharjah Sharjah United Arab Emirates Department of Computer Science Khalifa University of Science and Technology Masdar Institute Abu Dhabi United Arab Emirates

ISBN: (纸本)9789897583193

Digital watermarking is an effective technique for protecting various databases against data copyright infringement, piracy, and data tampering in the columnar database. Increasing deployments of various database systems and their versatile applications have raised the need for better watermarking schemes that are tailored to the target database systems’ specific architecture. Most of the existing digital watermarking schemes do not take into consideration the side effects that watermarking might have on the database’s important characteristics such as data compression and overall performance. In this research, we propose a distortion-free fragile watermarking scheme for columnar database architecture without interfering its underlying data compression scheme and its overall performance. The proposed scheme is flexible and can be adapted to various distributions of data. We tested our proposed scheme on both synthetic and real-world data, and proved its effectiveness. Copyright © 2018 by SCITEPRESS – Science and technology Publications, Lda. All rights reserved

关键词： Database systems

Cryptanalysis of an elgamal-like cryptosystem based on matrices over group rings 1

学校读者我要写书评

暂无评论

12th Chinese Conference on Trusted Computing and Information security, CTCIS 2018

作者： Jia, Jianwei Wang, Houzhen Zhang, Huanguo Wang, Shijia Liu, Jinhui Huawei Technologies Co. Ltd. Xi’an710075 China School of Cyber Science and Engineering WuhanHubei430072 China Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education WuhanHubei430072 China Department of Statistics and Actuarial Science Simon Fraser University Burnaby Canada School of Computer Science Shaanxi Normal University Xi’an710062 China

ISBN: (数字)9789811359132

ISBN: (纸本)9789811359125

ElGamal cryptography is one of the most important Public Key Cryptography (PKC) since Diffie-Hellman exchanges was proposed, however these PKCs which are based on the hard problems that discrete logarithm problem and integer factorization problem are weak with advances in quantum computers. So some alternatives should be proposed. Majid Khan et al. proposed two ElGamal-like public-key encryption schemes based on large abelian subgroup of general linear group over a residue ring, however the two schemes were not long before it was proved unsafe by us. Then, Saba Inam and Rashid (2016) proposed an improved cryptosystem which can resist my attack on "NEURAL COMPUTING & APPLICATIONS". By analyzing the security of the public key cryptography, we propose an improved method of algebraic key-recovery attack in the polynomial computational complexity despiteing the designers’ claim the cryptosystem is optimal security. Besides, we provide corresponding practical attack example to illustrate the attack method in our cryptanalysis, which breaks instances claiming 80 bits of security less than one minute on a single desktop computer. © 2019, Springer Nature Singapore Pte Ltd.

关键词： Computational complexity