Thwarting Adversarial Examples: An $L_0$-Robust Sparse Fourier Transform

Mitali Bafna, Jack Murtagh, Nikhil Vyas

Neural Information Processing Systems 

In this work, we give a framework for improving the robustness of classifiers to adversaries with L0 noise budgets.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found