Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2019
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/1906.01354 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Inhaltsangabe:
- We provide a general framework for characterizing the trade-off between accuracy and robustness in supervised learning. We propose a method and define quantities to characterize the trade-off between accuracy and robustness for a given architecture, and provide theoretical insight into the trade-off. Specifically we introduce a simple trade-off curve, define and study an influence function that captures the sensitivity, under adversarial attack, of the optima of a given loss function. We further show how adversarial training regularizes the parameters in an over-parameterized linear model, recovering the LASSO and ridge regression as special cases, which also allows us to theoretically analyze the behavior of the trade-off curve. In experiments, we demonstrate the corresponding trade-off curves of neural networks and how they vary with respect to factors such as number of layers, neurons, and across different network structures. Such information provides a useful guideline to architecture selection.