A New Ensemble Adversarial Attack Powered by Long-term Gradient Memories

Abstract

Deep neural networks are vulnerable to adversarial attacks.

arXiv commentAccepted by AAAI2020

References in corpus (4)

• The Cityscapes Dataset for Semantic Urban Scene Understanding
• Deformable Convolutional Networks
• SalGAN: Visual Saliency Prediction with Generative Adversarial Networks
• Adversarial Examples for Semantic Segmentation and Object Detection