检索结果-内蒙古大学图书馆

Research on Text Classification Based on BERT-BiGRU Model

学校读者我要写书评

暂无评论

Journal of Physics: Conference Series 2021年第1期1746卷

作者： Qing Yu Ziyin Wang Kaiwen Jiang Tianjin Key Laboratory of Intelligence Computing and Network Security Tianjin University of Technology Tianjin China

Text classification is a typical application of natural language processing. At present, the most commonly used text classification method is deep learning. Meanwhile there are many difficulties in natural language processing, such as metaphor expression, semantic diversity and grammatical specificity. To solve these problems, this paper proposes the structure of BERT-BiGRU model. First, use the BERT model instead of the traditional word2vec model to represent the word vector, the word representation is calculated according to the context information, and it can be adjusted according to the meaning of word while the context information is fused. Secondly BiGRU model is attached to the BERT model, BiGRU model can extract the text information features from both directions at the same time. Multiple sets of experiments were set up and compared with the model proposed in this paper, according to the final experimental results, using the proposed BERT-BiGRU model for text classification, the final accuracy, recall and F1 score were all above 0.9. It shows that BERT-BiGRU model has good performance in the Chinese text classification task.

关键词：

A PUF-based Lightweight Authenticated Metering Data Collection Scheme with Privacy Protection in Smart Grid

学校读者我要写书评

暂无评论

A PUF-based Lightweight Authenticated Metering Data Collecti...

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

作者： Ya-Nan Cao Yujue Wang Yong Ding Haibin Zheng Zhenyu Guan Huiyong Wang Guangxi Key Laboratory of Cryptography and Information Security Guilin University of Electronic Technology Guilin China Hangzhou Innovation Institute Beihang University Hangzhou China Cyberspace Security Research Center Pengcheng Laboratory Shenzhen China School of Cyber Science and Technology Beihang University Beijing China School of Mathematics and Computing Science Guilin University of Electronic Technology Guilin China

The rapid development of information and communication technology has made great advancements to grid structure, but at the same time it has also brought new security and privacy challenges to smart grid. Metering data transmitted in insecure public networks are vulnerable to eavesdropping and tampering by other organizations or users. Also, smart meters exposed to the outside could be physically attacked. Many privacy-preserving authentication schemes in smart grid have been proposed in recent years. However, most of them cannot protect smart meters from physical attacks. In this paper, a new lightweight privacy-preserving authenticated data collection scheme (PAC) based on Physically Unclonable Functions (PUFs) is proposed. With the uniqueness property of PUFs, the proposed scheme can not only resist physical attacks, but also support key sharing and identity authentication. security analysis shows that the proposed scheme can guarantee the privacy of users and resist traditional attacks such as man-in-the-middle attacks, replay attacks, impersonation attacks and physical attacks. Experimental performance indicates that the proposed scheme has high efficiency and low interaction.

关键词： Data privacy Authentication Resists Impersonation attacks Data collection Physical unclonable function Picture archiving and communication systems

Abnormality Detection in Chest X-Ray Images Using Uncertainty Prediction Autoencoders 23rd

学校读者我要写书评

暂无评论

Abnormality Detection in Chest X-Ray Images Using Uncertaint...

23rd International Conference on Medical Image computing and Computer-Assisted Intervention, MICCAI 2020

作者： Mao, Yifan Xue, Fei-Fei Wang, Ruixuan Zhang, Jianguo Zheng, Wei-Shi Liu, Hongmei School of Data and Computer Science Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing MOE Guangzhou China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Pazhou Lab Guangzhou China Guangdong Province Key Laboratory of Information Security Technology Guangzhou China

ISBN: (纸本)9783030597245

Chest radiography is widely used in annual medical screening to check whether lungs are healthy or not. Therefore it would be desirable to develop an intelligent system to help clinicians automatically detect potential abnormalities in chest X-ray images. Here with only healthy X-ray images, we propose a new abnormality detection approach based on an autoencoder which outputs not only the reconstructed normal version of the input image but also a pixel-wise uncertainty prediction. Higher uncertainty often appears at normal region boundaries with relatively larger reconstruction errors, but not at potential abnormal regions in the lung area. Therefore the normalized reconstruction error by the uncertainty provides a natural measurement for abnormality detection in images. Experiments on two chest X-ray datasets show the state-of-the-art performance by the proposed approach. © 2020, Springer Nature Switzerland AG.

关键词： Forecasting

Analysis on the security of Satellite Internet 17th

学校读者我要写书评

暂无评论

Analysis on the Security of Satellite Internet

17th International Annual Conference on Cyber security, CNCERT 2020

作者： Cao, Huan Wu, Lili Chen, Yue Su, Yongtao Lei, Zhengchao Zhao, Chunping Beijing Key Laboratory of Mobile Computing and Pervasive Device Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China National Computer Network Emergency Response Technical Team/Coordination Center of China Beijing100029 China Beijing Sylincom Technology Co. Ltd. Beijing China

ISBN: (纸本)9789813349216

Satellite Internet (SI) is a new way to provide internet access all over the world. It will bring great convenience to international communication. Compared with the traditional communication networks, SI has a significant change in network architecture and communication model, which will have an important impact on national information network security. For example, the global interconnected SI consists of a large number of small satellites and each satellite has multi-beams to cover a vast area, which leads to the disorderly flow of information across the border, and greatly increases the difficulty of network protection. Therefore, it is necessary to closely track the development of SI and analyze security problems brought by SI. In this paper, we analyze the security risks of SI from the perspective of national security, network security and equipment security, and thirteen security issues have been summarized to provide reference for the healthy development of SI industry. © 2020, The Author(s).

关键词： network security

CIR-Net: Cross-modality Interaction and Refinement for RGB-D Salient Object Detection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Cong, Runmin Lin, Qinwei Zhang, Chen Li, Chongyi Cao, Xiaochun Huang, Qingming Zhao, Yao Institute of Information Science Beijing Jiaotong University Beijing100044 China Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China School of Computer Science and Engineering Nanyang Technological University Singapore School of Cyber Science and Technology Shenzhen Campus Sun Yat-sen University 518107 China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Peng Cheng Laboratory Shenzhen518055 China

Focusing on the issue of how to effectively capture and utilize cross-modality information in RGB-D salient object detection (SOD) task, we present a convolutional neural network (CNN) model, named CIR-Net, based on the novel cross-modality interaction and refinement. For the cross-modality interaction, 1) a progressive attention guided integration unit is proposed to sufficiently integrate RGB-D feature representations in the encoder stage, and 2) a convergence aggregation structure is proposed, which flows the RGB and depth decoding features into the corresponding RGB-D decoding streams via an importance gated fusion unit in the decoder stage. For the cross-modality refinement, we insert a refinement middleware structure between the encoder and the decoder, in which the RGB, depth, and RGB-D encoder features are further refined by successively using a self-modality attention refinement unit and a cross-modality weighting refinement unit. At last, with the gradually refined features, we predict the saliency map in the decoder stage. Extensive experiments on six popular RGB-D SOD benchmarks demonstrate that our network outperforms the state-of-the-art saliency detectors both qualitatively and quantitatively. The code and results can be found from the link of https://***. io/proj_***. © 2022, CC BY-NC-SA.

关键词： Object detection

A Collaborative Kernel Clustering Algorithm for Non-Linear Data in Peer-to-Peer networks 7

学校读者我要写书评

暂无评论

A Collaborative Kernel Clustering Algorithm for Non-Linear D...

7th International Conference on Information, Cybernetics, and Computational Social Systems, ICCSS 2020

作者： Wang, Ting Wang, Rongrong Zhou, Jin Jiang, Hui Han, Shiyuan Wang, Lin Chen, Yuehui Shandong Provincial Key Laboratory of Network Based Intelligent Computing University of Jinan Jinan250022 China Development and Test Center Chinabond Fintech Information Technology Co. Ltd. Beijing100032 China

ISBN: (纸本)9781728162461

Clustering is a process of dividing data according to their similarity. The existing collaborative clustering methods do not consider the idea of kernel, which are more suitable to deal with segmentation of linear data. In this paper, a distributed k-means algorithm based on the kernel method for nonlinear data is proposed. In addition, considering of the role of attribute weight, the weights are defined for attributes in the presented clustering approach. Experiments on 'aspherical' synthetic datasets and real-world datasets show that our method achieves better results, simultaneously, attribute weighting reveals important feature subsets. © 2020 IEEE.

关键词： Peer to peer networks

BABD: A Bitcoin Address Behavior Dataset for Pattern Analysis

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Xiang, Yuexin Lei, Yuchen Bao, Ding Ren, Wei Li, Tiantian Yang, Qingqing Liu, Wenmao Zhu, Tianqing Choo, Kim-Kwang Raymond School of Computer Science China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Intelligent Geo-Information Processing Wuhan430074 China NSFOCUS Technologies Group Co. Ltd China Henan Key Laboratory of Network Cryptography Technology Zhengzhou450001 China School of Computer Science University of Technology Sydney Sydney Australia Department of Information Systems and Cyber Security University of Texas at San Antonio San AntonioTX78249-0631 United States

Cryptocurrencies are no longer just the preferred option for cybercriminal activities on darknets, due to the increasing adoption in mainstream applications. This is partly due to the transparency associated with the underpinning ledgers, where any individual can access the record of a transaction record on the public ledger. In this paper, we build a dataset comprising Bitcoin transactions between 12 July 2019 and 26 May 2021. This dataset (hereafter referred to as BABD-13) contains 13 types of Bitcoin addresses, 5 categories of indicators with 148 features, and 544,462 labeled data, which is the largest labeled Bitcoin address behavior dataset publicly available to our knowledge. We then use our proposed dataset on common machine learning models, namely: k-nearest neighbors algorithm, decision tree, random forest, multilayer perceptron, and XGBoost. The results show that the accuracy rates of these machine learning models for the multi-classification task on our proposed dataset are between 93.24% and 97.13%. We also analyze the proposed features and their relationships from the experiments, and propose a k-hop subgraph generation algorithm to extract a k-hop subgraph from the entire Bitcoin transaction graph constructed by the directed heterogeneous multigraph starting from a specific Bitcoin address node (e.g., a known transaction associated with a criminal investigation). Besides, we initially analyze the behavior patterns of different types of Bitcoin addresses according to the extracted *** Codes 68-11 Copyright © 2022, The Authors. All rights reserved.

关键词： Decision trees

On The Uncertainty Principle of Neural networks

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhang, Jun-Jie Zhang, Dong-Xiao Chen, Jian-Nan Pang, Long-Gang Meng, Deyu Division of Computational physics and Intelligent modeling Institute of Nuclear Technology Shaanxi Xi’an710024 China Key Laboratory of Quark & Lepton Physics Ministry of Education Central China Normal University Hubei Wuhan30079 China School of Mathematics and Statistics Ministry of Education Key Lab of Intelligent Networks and Network Security Xi’an Jiaotong University Shaanxi Xi’an710049 China

In this study, we explore the inherent trade-off between accuracy and robustness in neural networks, drawing an analogy to the uncertainty principle in quantum mechanics. We propose that neural networks are subject to an uncertainty relation, which manifests as a fundamental limitation in their ability to simultaneously achieve high accuracy and robustness against adversarial attacks. Through mathematical proofs and empirical evidence, we demonstrate that this trade-off is a natural consequence of the sharp boundaries formed between different class concepts during training. Our findings reveal that the complementarity principle, a cornerstone of quantum physics, applies to neural networks, imposing fundamental limits on their capabilities in simultaneous learning of conjugate features. Meanwhile, our work suggests that achieving human-level intelligence through a single network architecture or massive datasets alone may be inherently limited. Our work provides new insights into the theoretical foundations of neural network vulnerability and opens up avenues for designing more robust neural network architectures. © 2022, CC0.

关键词： Adversarial machine learning

Revisiting Token Dropping Strategy in Efficient BERT Pretraining

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhong, Qihuang Ding, Liang Liu, Juhua Liu, Xuebo Zhang, Min Du, Bo Tao, Dacheng National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China JD Explore Academy China Research Center for Graphic Communication Printing and Packaging Institute of Artificial Intelligence Wuhan University China Institute of Computing and Intelligence Harbin Institute of Technology China University of Sydney Australia

Token dropping is a recently-proposed strategy to speed up the pretraining of masked language models, such as BERT, by skipping the computation of a subset of the input tokens at several middle layers. It can effectively reduce the training time without degrading much performance on downstream tasks. However, we empirically find that token dropping is prone to a semantic loss problem and falls short in handling semantic-intense tasks (§2). Motivated by this, we propose a simple yet effective semantic-consistent learning method (SCTD) to improve the token dropping. SCTD aims to encourage the model to learn how to preserve the semantic information in the representation space. Extensive experiments on 12 tasks show that, with the help of our SCTD, token dropping can achieve consistent and significant performance gains across all task types and model sizes. More encouragingly, SCTD saves up to 57% of pretraining time and brings up to +1.56% average improvement over the vanilla token dropping. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics