检索结果-内蒙古大学图书馆

11th International Conference on Computer Engineering and Networks, CENet2021

作者： Zhao, Junxia Li, Lang Li, Qiuping Hengyang Normal University Hengyang421002 China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang421002 China

ISBN: (纸本)9789811665530

Recently, due to the development and popularization of communication and computing technologies, new technologies have emerged one after another. The Internet of Things (IoT) is a state-of-the-art technology that is applicable to all fields. The rapid development of the IoT seriously threatens the security of restricted devices. Lightweight block ciphers, as the main security measures for restricted devices, have attracted the attention of more and more researchers. The diffusion layer is an important part of the lightweight block cipher. Its design not only affects the security of lightweight block ciphers, but also has an important impact on its efficiency in hardware and software implementation. In this paper, we research and analyze the design principle and method of the lightweight block cipher diffusion layer. In addition, combined with the characteristics of lightweight cipher and its application environment, we point out that the diffusion layer of lightweight cipher is worthy of further research in the future. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Constructions of Lightweight MDS Diffusion Layers from Hankel Matrices 9th

Constructions of Lightweight MDS Diffusion Layers from Hanke...

引用

9th International Conference on Computer Engineering and Networks, CENet2019

作者： Li, Qiuping Li, Lang Zhang, Jian Zhao, Junxia Li, Kangman Hengyang Normal University Hengyang421002 China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang421002 China

ISBN: (纸本)9789811537523

Maximal distance separable (MDS) matrices are used as optimal diffusion layers in many block ciphers and hash functions. Recently, the designers paid more attention to the lightweight MDS matrices because it can reduce the hardware resource. In this paper, we give a new method to construct the lightweight MDS matrices. We provide some theoretical results and two kinds of 4 × 4 lightweight Hankel MDS matrices. We also prove that the 2s × 2s involution Hankel MDS matrix does not exist in finite field. Furthermore, we searched the 4 × 4 Hankel MDS matrices over GL(4, F2) and GL(8, F2) that have the better s-XOR counts until now. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Hash functions

来源：评论

学校读者我要写书评

暂无评论

Interpretable Saliency Map for Deep Reinforcement Learning

Interpretable Saliency Map for Deep Reinforcement Learning

引用

2020 International Conference on Computer Big Data and Artificial Intelligence, ICCBDAI 2020

作者： Zheng, Hong Dai, Yinglong Yu, Fumin Hu, Yuezhen School of Physics and Electronics Hunan Normal University Changsha410081 China College of Liberal Arts and Sciences National University of Defense Technology Changsha410073 China Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha410081 China

Deep reinforcement learning (deep RL) achieved big successes with the advantage of deep learning techniques, while it also introduces the disadvantage of the model interpretability. Bad interpretability is a great obstacle for deep RL to be applied in real situations or human-machine interaction situations. Borrowed from the deep learning field, the techniques of saliency maps recently become popular to improve the interpretability of deep RL. However, the saliency maps still cannot provide specific and clear enough model interpretations for the behavior of deep RL agents. In this paper, we propose to use hierarchical conceptual embedding techniques to introduce prior-knowledge in the deep neural network (DNN) based models of deep RL agents and then generate the saliency maps for all the embedded factors. As a result, we can track and discover the important factors that influence the decisions of deep RL agents. © Published under licence by IOP Publishing Ltd.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

FPGA optimal implementation of PRINCE against power analysis attacks 5

FPGA optimal implementation of PRINCE against power analysis...

引用

5th International Conference on information Science and Cloud computing, ISCC 2017

作者： Zou, Yi Li, Lang College of Computer Science and Technology Hengyang Normal University Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang421002 China

The algorithm PRINCE proposed in ASIACRYPT 2012 is a lightweight cipher, currently suitable for the implementation on RFID Smart Card of the IoT. It's studied to achieve the optimal implementation of PRINCE encryption algorithm, and to add a fixed random mask to enhance the anti power attacking ability of PRINCE. In this paper, we constructed the same operations into a module called PrinceRound, and used counter to control the PrinceRound module, while the same round operation runs repeatedly. As a result, it can save registers and effectively reduce the amount of computation. Furthermore, we used a special method by adding the random mask to S-box. The experimental results show that the optimized PRINCE occupies area 9.8% fewer than original PRINCE on FPGA and the encryption with a fixed random mask can run correctly. Last but not least, our research is the first one about the implementation of PRINCE algorithm on FPGA, and can serve as a reference for further application of IOT encryption. © Copyright owned by the author(s).

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

An optimized aes masking method for resisting side channel analysis 8th

An optimized aes masking method for resisting side channel a...

引用

8th International Conference on Computer Engineering and Networks, CENet 2018

作者： Jiao, Ge Li, Lang Zou, Yi College of Computer Science and Technology Hengyang Normal University HengyangHunan421002 China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application HengyangHunan421002 China

ISBN: (纸本)9783030146795

In order to against the side channel analysis attack such as power, electromagnetic waves, and time attack, an optimized masking method is proposed for Advanced Encryption Standard (AES) algorithm in this paper. This scheme adopts random hamming distance mask and offset randomization strategy in the first two rounds, the last round and two rounds randomly selected in the middle of the AES algorithm to ensure the security of each intermediate value. The scheme then adopts fixed-value mask strategy in the five rounds in the middle, which can reduce the time and space consumption to recalculate S box, improve the efficiency of the algorithm and reduce the production cost. To compare with other defence methods, we build a power analysis platform and conduct extensive experiments. The experimental results show that our optimized AES masking method is more secure than the compared methods, and it is able to resist second-order correlation power analysis (CPA) attacks. © Springer Nature Switzerland AG 2020.

关键词： Hamming distance

来源：评论

学校读者我要写书评

暂无评论

Variational Graph Autoencoders Method Based on Attentional Mechanisms for Overlapping Community Detection 12th

Variational Graph Autoencoders Method Based on Attentional M...

引用

12th International Conference on Computer Engineering and Networks, CENet 2022

作者： Wen, Kunhui Lin, Mugang Zhu, Xuanying Zhao, Huihuang College of Computer Science and Technology Hengyang Normal University Hunan Hengyang421008 China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hunan Hengyang421008 China

ISBN: (纸本)9789811969003

Detecting overlapping communities of an attribute network is an important and difficult issue in network science. Traditional methods for overlapping community detection generally considered only its topological structure and neglected node attribute so that the detected communities could be inaccurate. Graph neural networks (GNN) have recently gained attention because of their learning representation ability for node attributes and the topology of a graph and demonstrating superior performance in natural language processing, data mining and pattern recognition, etc. However, GNN methods are still less for overlapping community detection. In this paper, we present an overlapping community detection method based on GNN for attribute networks. It applies a variational graph autoencoder based on attentional mechanisms to learn the representation of nodes in the graph and enhances the representation learning capability of GNN through semi-supervised learning. Various real-world networks of publicly available datasets are used to verify the effectiveness of the proposed approach. The experimental results show that the proposed method outperforms many other methods. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Prediction of GDP Carbon Emission Based on Grey Model and Neural Network 4th

Prediction of GDP Carbon Emission Based on Grey Model and Ne...

引用

4th EAI International Conference on Robotic Sensor Networks, 2020

作者： Zhang, Feng Zhao, Huihuang Ramasamy, Manimaran College of Computer Science and Technology Hengyang Normal University Hengyang China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang China

ISBN: (纸本)9783030704506

In order to improve the prediction accuracy of Gross Domestic Product (GDP) carbon emission, combining the advantages of grey prediction and neural network, a discrete grey neural network prediction model named DGMBP is established. This model not only has the advantages of less data sample and larger development coefficient range of GM 1,1 model but also combines the advantages of neural network to deal with nonlinear data sample. Taking the GDP carbon emission data of China, India, the United States and the European Union as an example, the prediction results obtained are stable, and the accuracy of the prediction data is over 95%, which is much higher than that obtained by the linear regression equation and the logical regression equation. Finally, the carbon emission of GDP in 2020–2030 is predicted by using this model. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Simple and Efficient Knowledge Graph Attention Network for Recommendation

Simple and Efficient Knowledge Graph Attention Network for R...

引用

2023 International Conference on Cyber-Physical Social Intelligence, ICCSI 2023

作者： Li, Yangding Fu, Shaobin Feng, Hao Zeng, Yangyang Wang, Jinghao Jiang, Zhihao Zhang, Lvyun Hunan Provincial Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University School of Information Science and Engineering Changsha China Shenzhen Lazada Software Technology Company Limited Shenzhen China Hechi University School of Big Data and Computer Science Guangxi China

ISBN: (纸本)9798350312492

Existing methods for modeling recommendation systems based on knowledge graphs include embedding-based, pathbased, and propagation-based methods. The embedding-based approach is flexible but more suitable for intra-graph applications, the path-based approach can model complex relationships but has a high computational cost, and the propagation-based approach considers global information but may introduce noise. This study proposed a simple and efficient model, called SEKGAT, which comprehensive the ideology of path-based and propagation approach to personalized recommendation by aggregating the user preferences through graph attention mechanism and fusing multiple feature representations on the knowledge graph into item features through pooling aggregators. Experimental results for the CTR prediction and Top-K recommendation tasks on three datasets of real-world scenarios show that our model approach is competitive. © 2023 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

A throughput aware with collision-free MAC for wireless LANs

引用

Science China(information Sciences) 2016年第2期59卷 240-242页

作者： Tingrui PEI Yafeng DENG Zhetao LI Gengming ZHU Gaofeng PAN Youngjune CHOI Hiroo SEKIYA College of Information Engineering Xiangtan University Key Laboratory of Intelligent Computing & Information Processing of Ministry of Education Xiangtan University School of Computer Science & Engineering Hunan University of Science and Technology School of Electronic and Information Engineering Southwest University Department of Information and Computer Engineering Ajou University Graduate School of Advanced Integration Science Chiba University

Dear editor,The Carrier Sense Multiple Access with Collision Avoidance(CSMA/CA)hybrid with the resource reservation approach from Time Division Multiple Address(TDMA)has been emerged as a promising method to solve collision problems in wireless LANs[1–6].In the hybrid method,a TDMA circle contains multiple slots for nodes to contend for the ***,it allows a

关键词： MAC CSCF free TDMA A throughput aware with collision-free MAC for wireless LANs

来源：评论

学校读者我要写书评

暂无评论

Self-distillation Augmented Masked Autoencoders for Histopathological Image Classification

arXiv

引用

arXiv 2022年

作者： Luo, Yang Chen, Zhineng Zhou, Shengtian Gao, Xieping Fudan University Shanghai China Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University China

Self-supervised learning (SSL) has drawn increasing attention in histopathological image analysis in recent years. Compared to contrastive learning which is troubled with the false negative problem, i.e., semantically similar images are selected as negative samples, masked autoencoders (MAE) building SSL from a generative paradigm is probably a more appropriate pre-training. In this paper, we introduce MAE and verify the effect of visible patches for histopathological image understanding. Moreover, a novel SD-MAE model is proposed to enable a self-distillation augmented MAE. Besides the reconstruction loss on masked image patches, SD-MAE further imposes the self-distillation loss on visible patches to enhance the representational capacity of the encoder located shallow layer. We apply SD-MAE to histopathological image classification, cell segmentation and object detection. Experiments demonstrate that SD-MAE shows highly competitive performance when compared with other SSL methods in these tasks. © 2022, CC BY-NC-SA.

关键词： Distillation

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：