【论文阅读】DaST: Data-free Substitute Training for Adversarial Attacks（2020）Machine learning models（机器学习模型） are vulnerable（容易受到） to adversarial examples（对抗样本）. For the black-box setting（对于黑盒设置）, current substitute attacks（目前替代攻击） need pre-trained models（预训练模型） to generate adversarial examples（生成对抗样本）. However, pre-trained models（