Federated Learning(FL)enables joint training over distributed devices without data exchange but is highly vulnerable to attacks by adversaries in the form of model poisoning and malicious update injection.This work pr...Federated Learning(FL)enables joint training over distributed devices without data exchange but is highly vulnerable to attacks by adversaries in the form of model poisoning and malicious update injection.This work proposes Secured-FL,a blockchain-based defensive framework that combines smart contract-based authentication,clustering-driven outlier elimination,and dynamic threshold adjustment to defend against adversarial attacks.The framework was implemented on a private Ethereum network with a Proof-of-Authority consensus algorithm to ensure tamper-resistant and auditable model updates.Large-scale simulation on the Cyber Data dataset,under up to 50%malicious client settings,demonstrates Secured-FL achieves 6%-12%higher accuracy,9%-15%lower latency,and approximately 14%less computational expense compared to the PPSS benchmark framework.Additional tests,including confusion matrices,ROC and Precision-Recall curves,and ablation tests,confirm the interpretability and robustness of the defense.Tests for scalability also show consistent performance up to 500 clients,affirming appropriateness to reasonably large deployments.These results make Secured-FL a feasible,adversarially resilient FL paradigm with promising potential for application in smart cities,medicine,and other mission-critical IoT deployments.展开更多
Urban areas are particularly vulnerable to surface water flooding in a changing environment.A large number of urban surface water flood models have been developed to derive flood inundations and support risk managemen...Urban areas are particularly vulnerable to surface water flooding in a changing environment.A large number of urban surface water flood models have been developed to derive flood inundations and support risk management.However,unlike fluvial and coastal flooding,urban pluvial flooding is often associated with shallow water and thus the model is difficult to validate with traditional monitoring data.In this study,we first developed a full two-dimensional(2D)hydrodynamic model for simulating surface water floods.We further evaluated the model performance with multisource data from flood incidents,including official reports and social media data.The model was tested in the cities of Baoji and Linyi,China,where two surface water flood events recently occurred and caused considerable losses and casualties.In total,350 localized flooding incidents were obtained for the two cities(220 in Baoji and 130 in Linyi)and 313 reports were retained after data cleaning(202 in Baoji and 111 in Linyi).Over 90%of the reported flood incidents fall in urban areas where water depths are predicted to be higher than 0.15 m.The results demonstrate that the model is able to derive the broad patterns of flood inundation at the city scale.The approach tested here could be applied to other flood-prone cities and future research could include water depth information for more robust model validation.展开更多
文摘Federated Learning(FL)enables joint training over distributed devices without data exchange but is highly vulnerable to attacks by adversaries in the form of model poisoning and malicious update injection.This work proposes Secured-FL,a blockchain-based defensive framework that combines smart contract-based authentication,clustering-driven outlier elimination,and dynamic threshold adjustment to defend against adversarial attacks.The framework was implemented on a private Ethereum network with a Proof-of-Authority consensus algorithm to ensure tamper-resistant and auditable model updates.Large-scale simulation on the Cyber Data dataset,under up to 50%malicious client settings,demonstrates Secured-FL achieves 6%-12%higher accuracy,9%-15%lower latency,and approximately 14%less computational expense compared to the PPSS benchmark framework.Additional tests,including confusion matrices,ROC and Precision-Recall curves,and ablation tests,confirm the interpretability and robustness of the defense.Tests for scalability also show consistent performance up to 500 clients,affirming appropriateness to reasonably large deployments.These results make Secured-FL a feasible,adversarially resilient FL paradigm with promising potential for application in smart cities,medicine,and other mission-critical IoT deployments.
基金supported by the National Natural Science Foundation of China(Grant Nos:42371076,42271089,42461160294)the Key Project of Shanghai Municipal Education Commission(Grant No:2024AI01006)Shanghai Pilot Program for Basic Research(Grant No:TQ20240209)。
文摘Urban areas are particularly vulnerable to surface water flooding in a changing environment.A large number of urban surface water flood models have been developed to derive flood inundations and support risk management.However,unlike fluvial and coastal flooding,urban pluvial flooding is often associated with shallow water and thus the model is difficult to validate with traditional monitoring data.In this study,we first developed a full two-dimensional(2D)hydrodynamic model for simulating surface water floods.We further evaluated the model performance with multisource data from flood incidents,including official reports and social media data.The model was tested in the cities of Baoji and Linyi,China,where two surface water flood events recently occurred and caused considerable losses and casualties.In total,350 localized flooding incidents were obtained for the two cities(220 in Baoji and 130 in Linyi)and 313 reports were retained after data cleaning(202 in Baoji and 111 in Linyi).Over 90%of the reported flood incidents fall in urban areas where water depths are predicted to be higher than 0.15 m.The results demonstrate that the model is able to derive the broad patterns of flood inundation at the city scale.The approach tested here could be applied to other flood-prone cities and future research could include water depth information for more robust model validation.
