Research Article
Boosting Adversarial Attacks on Neural Networks with Better Optimizer
Table 3
Comparison of combined methods and original methods on attack success rates (%) against adversarially trained networks under the single-model setting.
| ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
The adversarial examples are generated on the ensemble of Inc-v3, Inc-v4, Incres-v2, and Res-101. |