Pub Date : 2022-05-20DOI: 10.1109/cvidliccea56201.2022.9825360
Jingxian Cui, Weimin Zhou, Weijun Liu
In recent years, with the development of deep learning and target detection, the accuracy of detection network is higher and higher, and the increase of network parameters and the decrease of inference speed. However, in actual application scenarios, the detection network needs to be deployed on some mobile or lightweight devices. To solve this problem, this paper proposes a method to compress the model. Based on YOLOv5s6 model, the channels with small weight are removed through sparse training and channel pruning, and then fix the model accuracy by knowledge distillation. Finally, the lightweight model Compressed YOLOv5s6 is obtained. The experimental result shows that the Compressed YOLOv5s6 model reduces 95.1% of the parameters, 30% of the inference speed and 90.2% of the model size compared with the original model, which is more suitable for the application of practical scenes.
{"title":"Target detection on lightweight device based on Compressed YOLOv5s6","authors":"Jingxian Cui, Weimin Zhou, Weijun Liu","doi":"10.1109/cvidliccea56201.2022.9825360","DOIUrl":"https://doi.org/10.1109/cvidliccea56201.2022.9825360","url":null,"abstract":"In recent years, with the development of deep learning and target detection, the accuracy of detection network is higher and higher, and the increase of network parameters and the decrease of inference speed. However, in actual application scenarios, the detection network needs to be deployed on some mobile or lightweight devices. To solve this problem, this paper proposes a method to compress the model. Based on YOLOv5s6 model, the channels with small weight are removed through sparse training and channel pruning, and then fix the model accuracy by knowledge distillation. Finally, the lightweight model Compressed YOLOv5s6 is obtained. The experimental result shows that the Compressed YOLOv5s6 model reduces 95.1% of the parameters, 30% of the inference speed and 90.2% of the model size compared with the original model, which is more suitable for the application of practical scenes.","PeriodicalId":23649,"journal":{"name":"Vision","volume":"17 1","pages":"274-277"},"PeriodicalIF":0.0,"publicationDate":"2022-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77238093","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-20DOI: 10.1109/cvidliccea56201.2022.9825050
Zizhi Ma
In terms of music genre classification, neural networks and machine learning models have their respective advantages. This paper aims to compare the performance and feature extraction capability between neural networks and traditional machine learning algorithms on music genre classification. All the components of 9 main music features, each with seven statistical values, were extracted as essential features, and different dimension reduction methods were applied. This paper compares the performance of training the features by neural networks and machine learning models. Finally, this paper used the output of layers in the neural networks as features and applied traditional machine learning models for training to see if their performance could be optimized. The result showed that the performance was raised by about 20%, compared to the essential features, and raised by about 5%, compared to the reduced features. So, it can be concluded that the feature extraction capability of neural networks is better than traditional machine learning models. Also, using features filtered by neural networks and applying traditional machine learning models for training is a method providing both excellent performance and high efficiency.
{"title":"Comparison between Machine Learning Models and Neural Networks on Music Genre Classification","authors":"Zizhi Ma","doi":"10.1109/cvidliccea56201.2022.9825050","DOIUrl":"https://doi.org/10.1109/cvidliccea56201.2022.9825050","url":null,"abstract":"In terms of music genre classification, neural networks and machine learning models have their respective advantages. This paper aims to compare the performance and feature extraction capability between neural networks and traditional machine learning algorithms on music genre classification. All the components of 9 main music features, each with seven statistical values, were extracted as essential features, and different dimension reduction methods were applied. This paper compares the performance of training the features by neural networks and machine learning models. Finally, this paper used the output of layers in the neural networks as features and applied traditional machine learning models for training to see if their performance could be optimized. The result showed that the performance was raised by about 20%, compared to the essential features, and raised by about 5%, compared to the reduced features. So, it can be concluded that the feature extraction capability of neural networks is better than traditional machine learning models. Also, using features filtered by neural networks and applying traditional machine learning models for training is a method providing both excellent performance and high efficiency.","PeriodicalId":23649,"journal":{"name":"Vision","volume":"43 1","pages":"189-194"},"PeriodicalIF":0.0,"publicationDate":"2022-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77418758","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-20DOI: 10.1109/cvidliccea56201.2022.9824593
X. Liu, Chenqi Li, Yu Chen
Using semantic segmentation technology based on a convolutional neural network (CNN) environment, urban open space orthophotos with typical feature segments collected by UAVs are used as the basis of neural network training data, and the U-net semantic segmentation algorithm research framework is used to import remotely sensed images into the algorithm model, encode the data with characterization, strengthen its behavioral features, and finally output the data with behavioral feature information This is used to build a training set of behavioral elements of the urban open space environment. Based on this training set, the training set can be used to classify and identify urban open spaces with similar environmental characteristics, thus quickly building a digital information model of environmental behavior elements in urban open spaces, improving the digital efficiency of environmental behavior research and saving a lot of time and cost for subsequent analysis.
{"title":"Research on urban open space behavior extraction based on semantic segmentation technology","authors":"X. Liu, Chenqi Li, Yu Chen","doi":"10.1109/cvidliccea56201.2022.9824593","DOIUrl":"https://doi.org/10.1109/cvidliccea56201.2022.9824593","url":null,"abstract":"Using semantic segmentation technology based on a convolutional neural network (CNN) environment, urban open space orthophotos with typical feature segments collected by UAVs are used as the basis of neural network training data, and the U-net semantic segmentation algorithm research framework is used to import remotely sensed images into the algorithm model, encode the data with characterization, strengthen its behavioral features, and finally output the data with behavioral feature information This is used to build a training set of behavioral elements of the urban open space environment. Based on this training set, the training set can be used to classify and identify urban open spaces with similar environmental characteristics, thus quickly building a digital information model of environmental behavior elements in urban open spaces, improving the digital efficiency of environmental behavior research and saving a lot of time and cost for subsequent analysis.","PeriodicalId":23649,"journal":{"name":"Vision","volume":"12 1","pages":"921-925"},"PeriodicalIF":0.0,"publicationDate":"2022-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76337460","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-20DOI: 10.1109/cvidliccea56201.2022.9825086
Yi Wang, Shuizhou Ke, Shaohong Wang, Zhibo Zheng
Black rot, black measles and isariopsis leaf spot are three kinds of very fatal grapevine virus disease. In the cultivation of grape, these diseases will harm the growth of grapes and have a great impact on the yield. Thus, timely diagnosis and treatment measures in the early stage of disease will greatly reduce the mortality of grape, which is particularly important in the cultivation of grape. The traditional method of manual screening requires staff with professional knowledge of diseases and detection experience, which requires high labor cost and a lot of time in large-scale detection. We consider adding a convolution neural network based deep learning detection method in large-scale screening to quickly detect easily diagnosed cases so as to focus on the hard-to-discern cases and reduce work pressure. In this paper, we propose a detection scheme using advanced deep learning framework to identify these three diseases with similar symptoms, locate their positions in image visualization and outline them accurately. Numerical results reveal that the detection scheme has great performance, and the high-performance configuration is obtained through several experiments.
{"title":"A Grapevine Virus Disease Detection Method Based on Convolution Neural Network","authors":"Yi Wang, Shuizhou Ke, Shaohong Wang, Zhibo Zheng","doi":"10.1109/cvidliccea56201.2022.9825086","DOIUrl":"https://doi.org/10.1109/cvidliccea56201.2022.9825086","url":null,"abstract":"Black rot, black measles and isariopsis leaf spot are three kinds of very fatal grapevine virus disease. In the cultivation of grape, these diseases will harm the growth of grapes and have a great impact on the yield. Thus, timely diagnosis and treatment measures in the early stage of disease will greatly reduce the mortality of grape, which is particularly important in the cultivation of grape. The traditional method of manual screening requires staff with professional knowledge of diseases and detection experience, which requires high labor cost and a lot of time in large-scale detection. We consider adding a convolution neural network based deep learning detection method in large-scale screening to quickly detect easily diagnosed cases so as to focus on the hard-to-discern cases and reduce work pressure. In this paper, we propose a detection scheme using advanced deep learning framework to identify these three diseases with similar symptoms, locate their positions in image visualization and outline them accurately. Numerical results reveal that the detection scheme has great performance, and the high-performance configuration is obtained through several experiments.","PeriodicalId":23649,"journal":{"name":"Vision","volume":"41 1","pages":"36-40"},"PeriodicalIF":0.0,"publicationDate":"2022-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77686823","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-20DOI: 10.1109/cvidliccea56201.2022.9825218
Yang Pan
In medical image recognition represented by bone age prediction, image samples need to be preprocessed to improve the quality of image samples and improve the learning efficiency of deep learning. This paper aims to compare the effects of different image preprocessing methods on the performance of the neural network. In this paper, the method of control experiment is used. Without pretreatment, the structure and framework of the neural network are controlled to remain unchanged, to make the conclusion more objective. This paper mainly discusses three pretreatment methods. 1 Conventional image filtering; 2. Use u-net network specially used for biomedical image segmentation to segment hand bones in X-ray; 3. The control group did not undergo image preprocessing. At the same time, this paper proposes to mark the gender of the owner of hand bone X-ray film in the form of a white background mark on the original image and control the gender weight by adjusting the size of the mark. U-net network preprocessing does not significantly improve the accuracy of the neural network, but this method makes the effect of deep neural network and shallow neural network almost the same, so it can be used as an effective method to prevent overfitting of neural networks. The main innovation of this paper is to explore the effectiveness of preprocessing algorithms in preventing the overfitting of medical image models by comparing the bone age prediction under various preprocessing methods.
{"title":"Influence of different image preprocessing methods on bone age prediction","authors":"Yang Pan","doi":"10.1109/cvidliccea56201.2022.9825218","DOIUrl":"https://doi.org/10.1109/cvidliccea56201.2022.9825218","url":null,"abstract":"In medical image recognition represented by bone age prediction, image samples need to be preprocessed to improve the quality of image samples and improve the learning efficiency of deep learning. This paper aims to compare the effects of different image preprocessing methods on the performance of the neural network. In this paper, the method of control experiment is used. Without pretreatment, the structure and framework of the neural network are controlled to remain unchanged, to make the conclusion more objective. This paper mainly discusses three pretreatment methods. 1 Conventional image filtering; 2. Use u-net network specially used for biomedical image segmentation to segment hand bones in X-ray; 3. The control group did not undergo image preprocessing. At the same time, this paper proposes to mark the gender of the owner of hand bone X-ray film in the form of a white background mark on the original image and control the gender weight by adjusting the size of the mark. U-net network preprocessing does not significantly improve the accuracy of the neural network, but this method makes the effect of deep neural network and shallow neural network almost the same, so it can be used as an effective method to prevent overfitting of neural networks. The main innovation of this paper is to explore the effectiveness of preprocessing algorithms in preventing the overfitting of medical image models by comparing the bone age prediction under various preprocessing methods.","PeriodicalId":23649,"journal":{"name":"Vision","volume":"8 1","pages":"632-636"},"PeriodicalIF":0.0,"publicationDate":"2022-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75926074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-20DOI: 10.1109/cvidliccea56201.2022.9824845
Wenhua Cao, Shuqin Geng, Xiaohong Peng, Jingyao Nie, Xuefeng Li, Pengkun Li
With the development trend of the Intelligent Internet of Things (IoT) society, the infrastructure of the IoT is increasing, and the use of RFID technology as the core of the IoT system is also more extensive. Strengthening the security of IoT infrastructure has become a top priority. Most of these IoT infrastructures are resource constrained, so lightweight encryption algorithms are used to ensure the communication security between IoT devices. This paper proposes a lightweight encryption algorithm named “SWLEA”. The data block length of the algorithm is 32-bit, and supports 32-bit key. The algorithm is mainly applicable to the system with RFID tag chip as the identifier chip.
{"title":"A Lightweight Encryption Algorithm for RFID System","authors":"Wenhua Cao, Shuqin Geng, Xiaohong Peng, Jingyao Nie, Xuefeng Li, Pengkun Li","doi":"10.1109/cvidliccea56201.2022.9824845","DOIUrl":"https://doi.org/10.1109/cvidliccea56201.2022.9824845","url":null,"abstract":"With the development trend of the Intelligent Internet of Things (IoT) society, the infrastructure of the IoT is increasing, and the use of RFID technology as the core of the IoT system is also more extensive. Strengthening the security of IoT infrastructure has become a top priority. Most of these IoT infrastructures are resource constrained, so lightweight encryption algorithms are used to ensure the communication security between IoT devices. This paper proposes a lightweight encryption algorithm named “SWLEA”. The data block length of the algorithm is 32-bit, and supports 32-bit key. The algorithm is mainly applicable to the system with RFID tag chip as the identifier chip.","PeriodicalId":23649,"journal":{"name":"Vision","volume":"4 1","pages":"1094-1097"},"PeriodicalIF":0.0,"publicationDate":"2022-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79791520","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-20DOI: 10.1109/cvidliccea56201.2022.9825350
Bowen Duan, Aiqing Du, Peiyu Yang, Jiale Wang, Wenjiei Mou, Haiyu Ju
Matchmaking trading system has become an essential paradigm to leverage the massive buyers to obtain the certain trades in a most effective method. Trading matchmaking method is an indispensable issue in commerce platforms owing to sellers and buyers exiting in heterogeneous bidder and prices. Matchmaking method is a fundamental approach in trading platforms, while currently most researchers and systems are considered and relayed on a concentrated servers leads to ignore the server safety in assigning trading platforms and the risk of sensitive information leakage by utilizing a centralized server. In this paper, we concentrate on distributed matchmaking approach for buyers with diversity sellers in trading platforms and propose an allocation method DMTP to maximize the social welfare by utilizing the block chain trading technology with reasonable computation and communication costs. Extensively experimental results indicate that proposed mechanism can greatly enhance the successful ratio of matchmaking trades and compare proposed mechanism social welfare with exiting trading algorithms.
{"title":"DMTP: A Distributed Matchmaking Trading Platform","authors":"Bowen Duan, Aiqing Du, Peiyu Yang, Jiale Wang, Wenjiei Mou, Haiyu Ju","doi":"10.1109/cvidliccea56201.2022.9825350","DOIUrl":"https://doi.org/10.1109/cvidliccea56201.2022.9825350","url":null,"abstract":"Matchmaking trading system has become an essential paradigm to leverage the massive buyers to obtain the certain trades in a most effective method. Trading matchmaking method is an indispensable issue in commerce platforms owing to sellers and buyers exiting in heterogeneous bidder and prices. Matchmaking method is a fundamental approach in trading platforms, while currently most researchers and systems are considered and relayed on a concentrated servers leads to ignore the server safety in assigning trading platforms and the risk of sensitive information leakage by utilizing a centralized server. In this paper, we concentrate on distributed matchmaking approach for buyers with diversity sellers in trading platforms and propose an allocation method DMTP to maximize the social welfare by utilizing the block chain trading technology with reasonable computation and communication costs. Extensively experimental results indicate that proposed mechanism can greatly enhance the successful ratio of matchmaking trades and compare proposed mechanism social welfare with exiting trading algorithms.","PeriodicalId":23649,"journal":{"name":"Vision","volume":"90 1","pages":"252-255"},"PeriodicalIF":0.0,"publicationDate":"2022-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82818798","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-20DOI: 10.1109/cvidliccea56201.2022.9825243
Yabo Li, Z. Niu, Quan Sun, Huaitie Xiao
The images collected by CCD devices have the characteristics of low SNR (Signal-to-Noise Ratio) and complex background. In order to reduce the difficulty of target extraction, this paper uses real star images to train a background suppression network based on CBDNet [1], a denoising network structure. The experimental result shows that the network can effectively suppress the background and improve the SNR of the star points while retaining the detailed information of the star points.
{"title":"Background Suppression Method of Star Image Based on Improved CBDNet","authors":"Yabo Li, Z. Niu, Quan Sun, Huaitie Xiao","doi":"10.1109/cvidliccea56201.2022.9825243","DOIUrl":"https://doi.org/10.1109/cvidliccea56201.2022.9825243","url":null,"abstract":"The images collected by CCD devices have the characteristics of low SNR (Signal-to-Noise Ratio) and complex background. In order to reduce the difficulty of target extraction, this paper uses real star images to train a background suppression network based on CBDNet [1], a denoising network structure. The experimental result shows that the network can effectively suppress the background and improve the SNR of the star points while retaining the detailed information of the star points.","PeriodicalId":23649,"journal":{"name":"Vision","volume":"24 1","pages":"671-674"},"PeriodicalIF":0.0,"publicationDate":"2022-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81774063","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-20DOI: 10.1109/cvidliccea56201.2022.9824485
Yi Lin
Nowadays, various neural network models are updated, and most industries around the world need deep learning algorithms to solve a lot of practical problems. In this paper, we propose the task of image recognition of ancient Chinese characters based on RESNET network model, in order to provide help for students to learn ancient Chinese characters. In the work, the classification of five ancient Chinese characters is completed. The results of RESNET network model are very good, and the accuracy of the final result of the test set is 90%. At the same time, the stability of the model was tested after training, including vertical and horizontal flipping of the image of the test set, and adding noise to the image of the test set. Finally, the RESNET network model is summarized and its applicable environment is described.
{"title":"Ancient Character Image Classification Model Training","authors":"Yi Lin","doi":"10.1109/cvidliccea56201.2022.9824485","DOIUrl":"https://doi.org/10.1109/cvidliccea56201.2022.9824485","url":null,"abstract":"Nowadays, various neural network models are updated, and most industries around the world need deep learning algorithms to solve a lot of practical problems. In this paper, we propose the task of image recognition of ancient Chinese characters based on RESNET network model, in order to provide help for students to learn ancient Chinese characters. In the work, the classification of five ancient Chinese characters is completed. The results of RESNET network model are very good, and the accuracy of the final result of the test set is 90%. At the same time, the stability of the model was tested after training, including vertical and horizontal flipping of the image of the test set, and adding noise to the image of the test set. Finally, the RESNET network model is summarized and its applicable environment is described.","PeriodicalId":23649,"journal":{"name":"Vision","volume":"45 1","pages":"50-54"},"PeriodicalIF":0.0,"publicationDate":"2022-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82569542","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-20DOI: 10.1109/cvidliccea56201.2022.9824528
Yuechen Hao
With the explosion of Nakamoto’s paper, blockchain technology has developed rapidly, but at the same time, security problems are emerging one after another. As a potential security hazard in the payment field, 51% attack brings huge risks to the normal operation of the blockchain system. Miners with great computing power have the ability to monopolize the generation of blocks and modify the generated blocks. Therefore, it is necessary to do research of this kind of attacks. This article cites both Nakamoto model and Rosenfeld model to illustrate relationship between computing power and attack success rate. Through a series of mining experiments, this paper preliminarily introduces the operation principles of blockchain based on Ethereum, including proof of stake, smart contracts etc. Models show that for rational attackers who pursue interests, they lack the motivation to launch 51% attacks. For attackers who only destroy the bitcoin system, they need to master huge financial resources to launch 51% of attacks, and even need financial support at the national level, which is very difficult. It can be said that 51% attacks against bitcoin are only theoretically possible, but users still need to pay enough attention. As an emerging technology, blockchain technology is currently in the research and exploration stage. While it is applied in the financial field, it is also expanding to other fields. In the future, blockchain technology will not only be used to solve the trust and security problems in the centralized service architecture, but also appear in more decentralized service scenarios. So, the research on blockchain security is particularly important.
{"title":"Research of the 51% attack based on blockchain","authors":"Yuechen Hao","doi":"10.1109/cvidliccea56201.2022.9824528","DOIUrl":"https://doi.org/10.1109/cvidliccea56201.2022.9824528","url":null,"abstract":"With the explosion of Nakamoto’s paper, blockchain technology has developed rapidly, but at the same time, security problems are emerging one after another. As a potential security hazard in the payment field, 51% attack brings huge risks to the normal operation of the blockchain system. Miners with great computing power have the ability to monopolize the generation of blocks and modify the generated blocks. Therefore, it is necessary to do research of this kind of attacks. This article cites both Nakamoto model and Rosenfeld model to illustrate relationship between computing power and attack success rate. Through a series of mining experiments, this paper preliminarily introduces the operation principles of blockchain based on Ethereum, including proof of stake, smart contracts etc. Models show that for rational attackers who pursue interests, they lack the motivation to launch 51% attacks. For attackers who only destroy the bitcoin system, they need to master huge financial resources to launch 51% of attacks, and even need financial support at the national level, which is very difficult. It can be said that 51% attacks against bitcoin are only theoretically possible, but users still need to pay enough attention. As an emerging technology, blockchain technology is currently in the research and exploration stage. While it is applied in the financial field, it is also expanding to other fields. In the future, blockchain technology will not only be used to solve the trust and security problems in the centralized service architecture, but also appear in more decentralized service scenarios. So, the research on blockchain security is particularly important.","PeriodicalId":23649,"journal":{"name":"Vision","volume":"09 1","pages":"278-283"},"PeriodicalIF":0.0,"publicationDate":"2022-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86502960","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：