 PixelDefend: Leveraging Generative Models to Understand and Defend
against Adversarial ExamplesInternational Conference on Learning Representations (ICLR), 2017 |
 A Saak Transform Approach to Efficient, Scalable and Robust Handwritten
Digits RecognitionPicture Coding Symposium (PCS), 2017 |
 Certifying Some Distributional Robustness with Principled Adversarial
TrainingInternational Conference on Learning Representations (ICLR), 2017 |
 Interpretation of Neural Networks is FragileAAAI Conference on Artificial Intelligence (AAAI), 2017 |
 One pixel attack for fooling deep neural networksIEEE Transactions on Evolutionary Computation (IEEE TEVC), 2017 |
 |
