FedSPA Uses Shapley Values to Shield Federated Learning From Poisoning Attacks
FedSPA combines Shapley-value analysis and model parameter similarity to identify malicious clients in federated learning under data poisoning attacks.
FedSPA combines Shapley-value analysis and model parameter similarity to identify malicious clients in federated learning under data poisoning attacks.
A PLOS One study combines Shapley values, Nash equilibrium, and Markov decision processes to build a dynamic integration model that ...
A new three-step quantitative framework combining AHP-TOPSIS, Shapley value, and evolutionary game models matched three Chinese regions with distinct land ...
An open-source R package uses Shapley values to attribute changes in healthy life expectancy to individual diseases without ordering bias, ...
Researchers at Shanghai Polytechnic University have developed CDAFIM, a class-difficulty-aware incentive mechanism that uses Shapley values to fairly reward federated ...
© 2025 Scienmag - Science Magazine
© 2025 Scienmag - Science Magazine