How To Backdoor Federated Learning

Eugene Bagdasaryan, Andreas Veit, Yiqing Hua et al.

2018 · arXiv (Cornell University) · 1,494 citations

Federated learning enables thousands of participants to construct a deep learning model without sharing their private training data with each other. For example, multiple smartphones can jointly train a next-word predictor for keyboards without revealing what individual users type. We demonstrate that any participant in federated learning can introduce hidden backdoor functionality into the joint global model, e.g., to ensure that an image classifier assigns an attacker-chosen label to images with certain features, or that a word predictor completes certain sentences with an attacker-chosen w…

Read the paper →

Explore this paper's citation graph on Constellation.