Abstract | ||
---|---|---|
We propose a new technique for deriving the differential privacy parameters in federated learning (FL). We consider the setting where a machine learning model is iteratively trained using stochastic gradient descent (SGD) and only the last update is publicly released. In this approach, we interpret each training iteration as a Markov kernel. We then quantify the impact of the kernel on privacy par... |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/ISIT45174.2021.9518124 | 2021 IEEE International Symposium on Information Theory (ISIT) |
Keywords | DocType | ISBN |
Training,Privacy,Differential privacy,Adaptation models,Tensors,Machine learning,Markov processes | Conference | 978-1-5386-8209-8 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shahab Asoodeh | 1 | 6 | 5.53 |
Wei-Ning Chen | 2 | 0 | 0.34 |
Flávio du Pin Calmon | 3 | 0 | 2.03 |
Ayfer Özgür | 4 | 14 | 2.66 |