Federated learning for edge computing is a promising solution in the data booming era,which leverages the computation ability of each edge device to train local models and only shares the model gradients to the centra...Federated learning for edge computing is a promising solution in the data booming era,which leverages the computation ability of each edge device to train local models and only shares the model gradients to the central server.However,the frequently transmitted local gradients could also leak the participants’private data.To protect the privacy of local training data,lots of cryptographic-based Privacy-Preserving Federated Learning(PPFL)schemes have been proposed.However,due to the constrained resource nature of mobile devices and complex cryptographic operations,traditional PPFL schemes fail to provide efficient data confidentiality and lightweight integrity verification simultaneously.To tackle this problem,we propose a Verifiable Privacypreserving Federated Learning scheme(VPFL)for edge computing systems to prevent local gradients from leaking over the transmission stage.Firstly,we combine the Distributed Selective Stochastic Gradient Descent(DSSGD)method with Paillier homomorphic cryptosystem to achieve the distributed encryption functionality,so as to reduce the computation cost of the complex cryptosystem.Secondly,we further present an online/offline signature method to realize the lightweight gradients integrity verification,where the offline part can be securely outsourced to the edge server.Comprehensive security analysis demonstrates the proposed VPFL can achieve data confidentiality,authentication,and integrity.At last,we evaluate both communication overhead and computation cost of the proposed VPFL scheme,the experimental results have shown VPFL has low computation costs and communication overheads while maintaining high training accuracy.展开更多
In this paper,a simple and robust shock-capturing method is developed for the Flux Reconstruction(FR)framework by combining the Adaptive Mesh Refinement(AMR)technique with the positivity-preserving property.The adapti...In this paper,a simple and robust shock-capturing method is developed for the Flux Reconstruction(FR)framework by combining the Adaptive Mesh Refinement(AMR)technique with the positivity-preserving property.The adaptive technique avoids the use of redundant meshes in smooth regions,while the positivity-preserving property makes the solver capable of providing numerical solutions with physical meaning.The compatibility of these two significant features relies on a novel limiter designed for mesh refinements.It ensures the positivity of solutions on all newly created cells.Therefore,the proposed method is completely positivity-preserving and thus highly robust.It performs well in solving challenging problems on highly refined meshes and allows the transition of cells at different levels to be completed within a very short distance.The performance of the proposed method is examined in various numerical experiments.When solving Euler equations,the technique of Local Artificial Diffusivity(LAD)is additionally coupled to damp oscillations.More importantly,when solving Navier-Stokes equations,the proposed method requires no auxiliaries and can provide satisfying numerical solutions directly.The implementation of the method becomes rather simple.展开更多
基金supported by the National Natural Science Foundation of China(No.62206238)the Natural Science Foundation of Jiangsu Province(Grant No.BK20220562)the Natural Science Research Project of Universities in Jiangsu Province(No.22KJB520010).
文摘Federated learning for edge computing is a promising solution in the data booming era,which leverages the computation ability of each edge device to train local models and only shares the model gradients to the central server.However,the frequently transmitted local gradients could also leak the participants’private data.To protect the privacy of local training data,lots of cryptographic-based Privacy-Preserving Federated Learning(PPFL)schemes have been proposed.However,due to the constrained resource nature of mobile devices and complex cryptographic operations,traditional PPFL schemes fail to provide efficient data confidentiality and lightweight integrity verification simultaneously.To tackle this problem,we propose a Verifiable Privacypreserving Federated Learning scheme(VPFL)for edge computing systems to prevent local gradients from leaking over the transmission stage.Firstly,we combine the Distributed Selective Stochastic Gradient Descent(DSSGD)method with Paillier homomorphic cryptosystem to achieve the distributed encryption functionality,so as to reduce the computation cost of the complex cryptosystem.Secondly,we further present an online/offline signature method to realize the lightweight gradients integrity verification,where the offline part can be securely outsourced to the edge server.Comprehensive security analysis demonstrates the proposed VPFL can achieve data confidentiality,authentication,and integrity.At last,we evaluate both communication overhead and computation cost of the proposed VPFL scheme,the experimental results have shown VPFL has low computation costs and communication overheads while maintaining high training accuracy.
基金supported by the National Natural Science Foundation of China(No.11721202).
文摘In this paper,a simple and robust shock-capturing method is developed for the Flux Reconstruction(FR)framework by combining the Adaptive Mesh Refinement(AMR)technique with the positivity-preserving property.The adaptive technique avoids the use of redundant meshes in smooth regions,while the positivity-preserving property makes the solver capable of providing numerical solutions with physical meaning.The compatibility of these two significant features relies on a novel limiter designed for mesh refinements.It ensures the positivity of solutions on all newly created cells.Therefore,the proposed method is completely positivity-preserving and thus highly robust.It performs well in solving challenging problems on highly refined meshes and allows the transition of cells at different levels to be completed within a very short distance.The performance of the proposed method is examined in various numerical experiments.When solving Euler equations,the technique of Local Artificial Diffusivity(LAD)is additionally coupled to damp oscillations.More importantly,when solving Navier-Stokes equations,the proposed method requires no auxiliaries and can provide satisfying numerical solutions directly.The implementation of the method becomes rather simple.
