2 papers
cs.CV2021
Adversarial example generation with AdaBelief Optimizer and Crop Invariance
Bo Yang, Hengwei Zhang, Yuchen Zhang +2
Deep neural networks are vulnerable to adversarial examples, which are crafted by applying small, human-imperceptible perturbations on the original images, so as to mislead deep ne…
cs.CV2020
Boosting Adversarial Attacks on Neural Networks with Better Optimizer
Heng Yin, Hengwei Zhang, Jindong Wang +1
Convolutional neural networks have outperformed humans in image recognition tasks, but they remain vulnerable to attacks from adversarial examples. Since these data are crafted by…