A game-based approximate verification of deep neural networks with provable guarantees
Despite the improved accuracy of deep neural networks, the discovery of adversarial examples has raised serious safety concerns. In this paper, we study two variants of pointwise robustness, the maximum safe radius problem, which for a given input sample computes the minimum distance to an adversari...
Main Authors: | , , , , |
---|---|
Format: | Journal article |
Language: | English |
Published: |
Elsevier
2019
|