Data sharing and privacy protection are made possible by federated learning,which allows for continuous model parameter sharing between several clients and a central server.Multiple reliable and high-quality clients m...Data sharing and privacy protection are made possible by federated learning,which allows for continuous model parameter sharing between several clients and a central server.Multiple reliable and high-quality clients must participate in practical applications for the federated learning global model to be accurate,but because the clients are independent,the central server cannot fully control their behavior.The central server has no way of knowing the correctness of the model parameters provided by each client in this round,so clients may purposefully or unwittingly submit anomalous data,leading to abnormal behavior,such as becoming malicious attackers or defective clients.To reduce their negative consequences,it is crucial to quickly detect these abnormalities and incentivize them.In this paper,we propose a Federated Learning framework for Detecting and Incentivizing Abnormal Clients(FL-DIAC)to accomplish efficient and security federated learning.We build a detector that introduces an auto-encoder for anomaly detection and use it to perform anomaly identification and prevent the involvement of abnormal clients,in particular for the anomaly client detection problem.Among them,before the model parameters are input to the detector,we propose a Fourier transform-based anomaly data detectionmethod for dimensionality reduction in order to reduce the computational complexity.Additionally,we create a credit scorebased incentive structure to encourage clients to participate in training in order tomake clients actively participate.Three training models(CNN,MLP,and ResNet-18)and three datasets(MNIST,Fashion MNIST,and CIFAR-10)have been used in experiments.According to theoretical analysis and experimental findings,the FL-DIAC is superior to other federated learning schemes of the same type in terms of effectiveness.展开更多
Today, in the field of computer networks, new services have been developed on the Internet or intranets, including the mail server, database management, sounds, videos and the web server itself Apache. The number of s...Today, in the field of computer networks, new services have been developed on the Internet or intranets, including the mail server, database management, sounds, videos and the web server itself Apache. The number of solutions for this server is therefore growing continuously, these services are becoming more and more complex and expensive, without being able to fulfill the needs of the users. The absence of benchmarks for websites with dynamic content is the major obstacle to research in this area. These users place high demands on the speed of access to information on the Internet. This is why the performance of the web server is critically important. Several factors influence performance, such as server execution speed, network saturation on the internet or intranet, increased response time, and throughputs. By measuring these factors, we propose a performance evaluation strategy for servers that allows us to determine the actual performance of different servers in terms of user satisfaction. Furthermore, we identified performance characteristics such as throughput, resource utilization, and response time of a system through measurement and modeling by simulation. Finally, we present a simple queue model of an Apache web server, which reasonably represents the behavior of a saturated web server using the Simulink model in Matlab (Matrix Laboratory) and also incorporates sporadic incoming traffic. We obtain server performance metrics such as average response time and throughput through simulations. Compared to other models, our model is conceptually straightforward. The model has been validated through measurements and simulations during the tests that we conducted.展开更多
基金supported by Key Research and Development Program of China (No.2022YFC3005401)Key Research and Development Program of Yunnan Province,China (Nos.202203AA080009,202202AF080003)+1 种基金Science and Technology Achievement Transformation Program of Jiangsu Province,China (BA2021002)Fundamental Research Funds for the Central Universities (Nos.B220203006,B210203024).
文摘Data sharing and privacy protection are made possible by federated learning,which allows for continuous model parameter sharing between several clients and a central server.Multiple reliable and high-quality clients must participate in practical applications for the federated learning global model to be accurate,but because the clients are independent,the central server cannot fully control their behavior.The central server has no way of knowing the correctness of the model parameters provided by each client in this round,so clients may purposefully or unwittingly submit anomalous data,leading to abnormal behavior,such as becoming malicious attackers or defective clients.To reduce their negative consequences,it is crucial to quickly detect these abnormalities and incentivize them.In this paper,we propose a Federated Learning framework for Detecting and Incentivizing Abnormal Clients(FL-DIAC)to accomplish efficient and security federated learning.We build a detector that introduces an auto-encoder for anomaly detection and use it to perform anomaly identification and prevent the involvement of abnormal clients,in particular for the anomaly client detection problem.Among them,before the model parameters are input to the detector,we propose a Fourier transform-based anomaly data detectionmethod for dimensionality reduction in order to reduce the computational complexity.Additionally,we create a credit scorebased incentive structure to encourage clients to participate in training in order tomake clients actively participate.Three training models(CNN,MLP,and ResNet-18)and three datasets(MNIST,Fashion MNIST,and CIFAR-10)have been used in experiments.According to theoretical analysis and experimental findings,the FL-DIAC is superior to other federated learning schemes of the same type in terms of effectiveness.
文摘Today, in the field of computer networks, new services have been developed on the Internet or intranets, including the mail server, database management, sounds, videos and the web server itself Apache. The number of solutions for this server is therefore growing continuously, these services are becoming more and more complex and expensive, without being able to fulfill the needs of the users. The absence of benchmarks for websites with dynamic content is the major obstacle to research in this area. These users place high demands on the speed of access to information on the Internet. This is why the performance of the web server is critically important. Several factors influence performance, such as server execution speed, network saturation on the internet or intranet, increased response time, and throughputs. By measuring these factors, we propose a performance evaluation strategy for servers that allows us to determine the actual performance of different servers in terms of user satisfaction. Furthermore, we identified performance characteristics such as throughput, resource utilization, and response time of a system through measurement and modeling by simulation. Finally, we present a simple queue model of an Apache web server, which reasonably represents the behavior of a saturated web server using the Simulink model in Matlab (Matrix Laboratory) and also incorporates sporadic incoming traffic. We obtain server performance metrics such as average response time and throughput through simulations. Compared to other models, our model is conceptually straightforward. The model has been validated through measurements and simulations during the tests that we conducted.
