论文标题
通过共同学习标签依赖性和成员模型的对抗合奏培训
Adversarial Ensemble Training by Jointly Learning Label Dependencies and Member Models
论文作者
论文摘要
培训各种子模型的合奏已在经验上被证明是改善深神经网络对抗性鲁棒性的有效策略。但是，当前用于图像识别的集合训练方法通常使用单速向量编码图像标签，该矢量忽略了标签之间的依赖关系。在本文中，我们提出了一种新颖的对抗性培训方法，该方法共同学习了标签依赖性和成员模型。我们的方法适应地利用了学习的标签依赖性，以在成员模型之间进行摩托学多样性。我们在包括MNIST，FashionMnist和CIFAR-10在内的广泛使用的数据集上评估了我们的方法，并表明与最先进的方法相比，它可以针对黑盒攻击实现出色的鲁棒性。我们的代码可在https://github.com/zjlab-ammi/lsd上找到。
Training an ensemble of diverse sub-models has been empirically demonstrated as an effective strategy for improving the adversarial robustness of deep neural networks. However, current ensemble training methods for image recognition typically encode image labels using one-hot vectors, which overlook dependency relationships between the labels. In this paper, we propose a novel adversarial en-semble training approach that jointly learns the label dependencies and member models. Our approach adaptively exploits the learned label dependencies to pro-mote diversity among the member models. We evaluate our approach on widely used datasets including MNIST, FashionMNIST, and CIFAR-10, and show that it achieves superior robustness against black-box attacks compared to state-of-the-art methods. Our code is available at https://github.com/ZJLAB-AMMI/LSD.
