检索结果-内蒙古大学图书馆

29th British Machine Vision Conference, BMVC 2018

作者： Xie, Jiafeng Shuai, Bing Hu, Jian-Fang Lin, Jingyang Zheng, Wei-Shi School of Data and Computer Science Sun Yat-sen University China Nanyang Technological University Singapore Guangdong Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing MOE Hong Kong

Recently, segmentation neural networks have been significantly improved by demonstrating very promising accuracies on public benchmarks. However, these models are very heavy and generally suffer from low inference speed, which limits their application scenarios in practice. Meanwhile, existing fast segmentation models usually fail to obtain satisfactory segmentation accuracies on public benchmarks. In this paper, we propose a teacher-student learning framework that transfers the knowledge gained by a heavy and better performed segmentation network (i.e. teacher) to guide the learning of fast segmentation networks (i.e. student). Specifically, both zero-order and first-order knowledge depicted in the fine annotated images and unlab.led auxiliary data are transferred to regularize our student learning. The proposed method can improve existing fast segmentation models without incurring extra computational overhead, so it can still process images with the same fast speed. Extensive experiments on the Pascal Context, Cityscape and VOC 2012 datasets demonstrate that the proposed teacher-student learning framework is able to significantly boost the performance of student network. © 2018. The copyright of this document resides with its authors.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Which DGA family does a malicious domain name belong to 5

Which DGA family does a malicious domain name belong to

引用

5th IEEE International Conference on data science in Cyberspace, DSC 2020

作者： Zhang, Yunyi Wu, Yuelong Jin, Shuyuan Yat-sen University School of Data and Computer Science Sun Guangzhou China Cyberspace Security Research Center Peng Cheng Laboratory Shenzhen China GuangDong Key Laboratory of Information Security Technology Sun Yat-set University Guangzhou China

ISBN: (纸本)9781728195582

The Domain Generation Algorithm (DGA) is a technology that generates a large amount of domains in a short time, commonly applied to malware by malicious attackers to circumvent the security mechanisms, such as domain blacklist. Besides discovering DGA domains, identifying DGA families also is significant for detecting and analyzing malware, which provides security professionals with the perspective of comprehensive analysis. In this paper, we investigate 22 different DGA families and propose an effective approach to portray and classify DGA families, which utilizes the strong host association and family portrait to identify different DGA families among massive DGA domains. The approach mitigates the hurdle caused by the nearly 100 times data difference among different families, implementing DGA family clustering. The experimental results show that the proposed approach identifies all of the DGA families accurately in the network that contains six families. © 2020 IEEE.

关键词： Malware

来源：评论

学校读者我要写书评

暂无评论

A mutual authentication lightweight rfid protocol for iot devices 2nd

A mutual authentication lightweight rfid protocol for iot de...

引用

2nd International Cognitive Cities Conference, IC3 2019

作者： Lu, Yong Wang, Anxi Liu, Shuai School of Management Science and Engineering Nanjing University of Information Science and Technology Nanjing210044 China Guizhou Provincial Key Laboratory of Public Big Data GuiZhou University GuiyangGuizhou550025 China School of Computer and Software Nanjing University of Information Science and Technology Nanjing210044 China Guangdong Provincial Key Laboratory of Data Security and Privacy Protection Guangzhou510632 China

ISBN: (纸本)9789811561122

The IoT data security is a hot topic at a data time. Personal privacy data may be easily leaked to data collectors in an open network environment. If the collectors get enough data, they can analyze the habit and interest of every IoT user, which may give helpful advice or cause endless harass. RFID authentication protocol in IoT is a powerful way to avoid the essential data leaked to data collectors. The previous protocols protect the security of RFID system. But they cannot guard the privacy of RFID system. The protocol we proposed achieves both the privacy and security. © Springer Nature Singapore Pte Ltd 2020.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

An Ensemble of CapsNet and KSVM Using Feature Fusion: Application to COVID-19 Detection 3

An Ensemble of CapsNet and KSVM Using Feature Fusion: Applic...

引用

3rd International Conference on Pattern Recognition and Machine Learning, PRML 2022

作者： Aggrey, Esther Stacy E. B. Zhen, Qin Kodjiku, Seth Larweh Aidoo, Evans Fiasam, Linda Delali Mensah, Acheampong Edward University of Electronic Science & Technology of China School of Information & Software Engineering Chengdu China University of Electronic Science & Technology of China School of Information & Software Engineering Network and Data Security Key Lab of Sichuan Province Chengdu China Zhejiang Gongshang University School of Computer & Information Engineering Hangzhou China

ISBN: (数字)9781665499507

ISBN: (纸本)9781665499507

COVID-19 virus is a major worldwide pandemic that is growing at a fast pace throughout the world. The usual approach for diagnosing COVID-19 is the use of a real-time polymerase chain reaction (RT-PCR) based nucleic acid test. However, RT-PCR has lower sensitivity in the early phases of COVID-19 detection. Recent studies have indicated that X-ray images may be useful throughout the early detection of the virus. Human screening has been shown to be cost-effective, susceptible to mistakes, and time-demanding, which has sparked an interest in using Convolutional Neural Networks (CNNs) to automate the process. CNNs, on the other hand, fail to view the exact placement of features as advantageous in medical imaging. Furthermore, for successful training and prediction, CNNs need a huge quantity of datasets. CNNs are rapidly reducing picture resolution, resulting in worsening accuracy in classification. We used newly created capsule networks (CapsNets) in our study to circumvent these disadvantages. The primary contribution is to improve the identification of SARS-CoV-2 with images obtained from X-ray by coupling capsule network with a kernel support vector machine (KSVM). The technique was evaluated using a publicly availab.e dataset, and the proposed model shows that the accuracy of the CapsNet-KSVM based model is improved by 94.6% accuracy, 95% sensitivity, and 98% specificity, which outperforms the traditional CNN and other existing ensemble models. The proposed CapsNet-KSVM based system can be employed to identify the presence of COVID-19 in the human body using X-ray images. © 2022 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Performance of Systematic Convolutional Low Density Generator Matrix Codes over Rayleigh Fading Channels with Impulsive Noise 3rd

Performance of Systematic Convolutional Low Density Generato...

引用

3rd International Conference on Space information Networks, SINC 2018

作者： Ji, Meiying Chen, Shengxiao Ma, Xiao School of Data and Computer Science Sun Yat-sen University Guangzhou510006 China School of Electronics and Information Technology Sun Yat-sen University Guangzhou510006 China Guangdong Key Laboratory of Information Security Technology Sun Yat-sen University Guangzhou510006 China

ISBN: (纸本)9789811359361

We investigate the systematic convolutional low density generator matrixÂ (SC-LDGM) codes over Rayleigh fading channels with symmetric alpha-stableÂ (SαS) impulsive noise. The performance is analyzed by deriving a lower bound based on an equivalent genie-aidedÂ (GA) system. Numerical simulations show that the SC-LDGM codes can achieve a significant gain compared to the convolutional codes over Rayleigh fading channels with impulsive noise. Numerical results also show that the performance of the SC-LDGM codes can be around one dB away from Shannon limits at the bit-error rateÂ (BER) of 10-5 and matches well with the GA lower bound in the low BER region. © 2019, Springer Nature Singapore Pte Ltd.

关键词： Impulse noise

来源：评论

学校读者我要写书评

暂无评论

Traffic Engineering in Dynamic Hybrid Segment Routing Networks

引用

computers, Materials & Continua 2021年第7期68卷 655-670页

作者： Yingya Guo Kai Huang Cheng Hu Jiangyuan Yao Siyu Zhou College of Mathematics and Computer Science Fuzhou UniversityFuzhou350000China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou UniversityFuzhou350000China Key Laboratory of Spatial Data Mining&Information Sharing Ministry of EducationFuzhou350003China School of Information Science and Technology Guangdong University of Foreign StudiesGuangzhou510006China School of Computer Science and Cyberspace Security Hainan UniversityHaiKou570228China Tandon School of Engineering New York UniversityNew York10012USA Department of Computing Hong Kong Polytechnic UniversityHong Hom999077Hong Kong

The emergence of Segment Routing(SR)provides a novel routing paradigm that uses a routing technique called source packet *** SR architecture,the paths that the packets choose to route on are indicated at the ingress *** with shortest-path-based routing in traditional distributed routing protocols,SR can realize a flexible routing by implementing an arbitrary flow splitting at the ingress *** the advantages of SR,it may be difficult to update the existing IP network to a full SR deployed network,for economical and technical *** partial of the traditional IP network to the SR network,thus forming a hybrid SR network,is a preferable *** the traffic is dynamically changing in a daily time,in this paper,we propose a Weight Adjustment algorithm WASAR to optimize routing in a dynamic hybrid SR *** algorithm can be divided into three steps:firstly,representative Traffic Matrices(TMs)and the expected TM are obtained from the historical TMs through ultrascalab.e spectral clustering ***,given the network topology,the initial network weight setting and the expected TM,we can realize the link weight optimization and SR node deployment optimization through a Deep Reinforcement Learning(DRL)***,we optimize the flow splitting ratios of SR nodes in a centralized online manner under dynamic traffic demands,in order to improve the network *** the evaluation,we exploit historical TMs to test the performance of the obtained routing configuration in *** extensive experimental results validate that our proposed WASAR algorithm has superior performance in reducing Maximum Link Utilization(MLU)under the dynamic traffic.

关键词： Traffic engineering routing optimization segment routing deep reinforcement learning ultra-scalab.e spectral clustering

来源：评论

学校读者我要写书评

暂无评论

Asymmetric group key agreement

Asymmetric group key agreement

引用

28th Annual International Conference on the Theory and Applications of Cryptographic Techniques, EUROCRYPT 2009

作者： Qianhong, Wu Yi, Mu Susilo, Willy Bo, Qin Domingo-Ferrer, Josep Universitat Rovira i Virgili Dept. of Comp. Eng. and Maths UNESCO Department of Data Privacy Tarragona Catalonia Spain Key Lab. of Aerospace Information Security and Trusted Computing School of Computer Wuhan University China Centre for Computer and Information Security Research School of Computer Science and Software Engineering University of Wollongong Australia Dept. of Maths School of Science Xi'an University of Technology China

ISBN: (纸本)3642010008

A group key agreement (GKA) protocol allows a set of users to establish a common secret via open networks. Observing that a major goal of GKAs for most applications is to establish a confiDential channel among group members, we revisit the group key agreement definition and distinguish the conventional (symmetric) group key agreement from asymmetric group key agreement (ASGKA) protocols. Instead of a common secret key, only a shared encryption key is negotiated in an ASGKA protocol. This encryption key is accessible to attackers and corresponds to different decryption keys, each of which is only computable by one group member. We propose a generic construction of one-round ASGKAs based on a new primitive referred to as aggregatable signaturebased broadcast (ASBB), in which the public key can be simultaneously used to verify signatures and encrypt messages while any signature can be used to decrypt ciphertexts under this public key. Using bilinear pairings, we realize an efficient ASBB scheme equippe d with useful properties. Following the generic construction, we instantiate a one-round ASGKA protocol tightly reduced to the decision Bilinear Diffie-Hellman Exponentiation (BDHE) assumption in the standard model. © International Association for Cryptologic Research 2009.

关键词： Public key cryptography

来源：评论

学校读者我要写书评

暂无评论

Block Markov superposition transmission of BCH codes with iterative hard-decision decoding

Block Markov superposition transmission of BCH codes with it...

引用

2017 IEEE International Symposium on information Theory, ISIT 2017

作者： Lin, Nina Cai, Suihua Ma, Xiao School of Electronics and Information Technology Sun Yat-sen University Guangzhou510006 China School of Data and Computer Science Sun Yat-sen University Guangzhou510006 China Guangdong Key Laboratory of Information Security Technology Sun Yat-sen University Guangzhou510006 China

ISBN: (纸本)9781509040964

This paper is concerned with block Markov super-position transmission of BCH (BMST-BCH) codes. Compared with other BMST codes, BMST-BCH codes can achieve a lower error floor with an encoding memory of two, which is critical to reduce both delay and implementation complexity. To further reduce the implementation complexity, we propose a hard-decision sliding-window decoding algorithm, in which only binary and/or erasure messages are processed and exchanged between nodes. A fast simulation approach is proposed, with the help of the genie-aided lower bound and the density evolution analysis, to evaluate the performance of BMST-BCH codes at the BER of 10-15. BMST-BCH codes are constructed with overheads ranging from 15% to 25%, exhibiting performances comparable to staircase codes with similar latencies. The proposed construction is more flexible to trade off latency against performance, and may find applications in optical transport networks as an attractive candidate. © 2017 IEEE.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Aided Network Architecture Generation for JPEG Image Steganalysis 20

Reinforcement Learning Aided Network Architecture Generation...

引用

8th ACM Workshop on information Hiding and Multimedia security, IH and MMSec 2020

作者： Yang, Jianhua Lu, Beiling Xiao, Liang Kang, Xiangui Shi, Yun-Qing Guangdong Key Lab of Information Security Sun Yat-Sen University Guangzhou Guangdong China Department of Communication Engineering Xiamen University Xiamen Fujian China School of Data and Computer Science Sun Yat-Sen University Guangzhou Guangdong China Department of ECE New Jersey Institute of Technology NewarkNJ United States

ISBN: (纸本)9781450370509

The architectures of convolutional neural networks used in steganalysis have been designed heuristically. In this paper, an automatic Network Architecture Generation algorithm based on reinforcement learning for JPEG image Steganalysis (JS-NAG) has been proposed. Different from the automatic neural network generation methods in computer vision which are based on the strong content signals, steganalysis is based on the weak embedded signals, thus needs specific design. In the proposed method, the agent is trained to sequentially select some high-performing blocks using Q-learning to generate networks. An early stop strategy and a well-designed performance prediction function have been utilized to reduce the search time. To generate the optimal networks, hundreds of networks have been searched and trained on 3 GPUs for 15 days. To further improve the detection accuracy, we make an ensemble classifier out of the generated convolutional neural networks. The experimental results have shown that the proposed method significantly outperforms the current state-of-the-art CNN based methods. © 2020 ACM.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Depthwise Separable Convolutional Neural Network for Image Forensics 34

Depthwise Separable Convolutional Neural Network for Image F...

引用

34th IEEE International Conference on Visual Communications and Image Processing, VCIP 2019

作者： Chen, Yifang Peng, Feng Kang, Xiangui Jane Wang, Z. Sun Yat-sen University Guangdong Key Lab of Information Security School of Data and Computer Science China ECE Dept University of British Colombia VancouverBCV6T 1Z4 Canada

ISBN: (纸本)9781728137230

General-purpose forensics on small image patches appears to be feasible and important, but in fact poses a challenge due to insufficient statistics. Furthermore, there is a need to develop a forensic approach that can automatically learn effective and robust features related to image forensics with high parameter efficiency. In this paper, we propose a depthwise separable convolutional neural network (CNN) for the simultaneous detection of eleven types of image manipulations in image patches. Different from the previous CNNs based on standard convolution, depthwise separable convolution is introduced in the proposed CNN to adaptively extract forensics-related features from image patches with better parameter efficiency. When compared with four state-of-The-Art methods, experiments demonstrate that the proposed CNN architecture can achieve better performance, e.g., the improvement in terms of accuracy in the detection of 32 × 32 images is up to 7.33%. It also achieves significantly better overall performance for different databases and better robustness against JPEG compression. © 2019 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：