NoPeek: Information leakage reduction to share activations in distributed deep learning
For distributed machine learning with sensitive data, we demonstrate how minimizing distance correlation between raw data and intermediary representations reduces leakage of sensitive raw data patterns across client communications while maintaining model accuracy. Leakage (measured using distance co...
| Main Authors: | , , , |
|---|---|
| Other Authors: | , |
| Format: | Article |
| Language: | English |
| Published: |
IEEE,
2022-07-18T14:30:57Z.
|
| Subjects: | |
| Online Access: | Get fulltext |