Let's Focus: Focused Backdoor Attack against Federated Transfer Learning

arXiv:2404.19420v1 Announce Type: new
Abstract: Federated Transfer Learning (FTL) is the most general variation of Federated Learning. According to this distributed paradigm, a feature learning pre-step is commonly carried out by only one party, typically the server, on publicly shared data. After that, the Federated Learning phase takes place to train a classifier collaboratively using the learned feature extractor. Each involved client contributes by locally training only the classification layers on a private training set. The peculiarity of an FTL …

abstract arxiv backdoor cs.cr cs.lg data distributed feature federated learning focus general paradigm server train transfer transfer learning type variation