Less is More: Culling the Training Set to Improve Robustness of Deep Neural Networks
Less is More: Culling the Training Set to Improve Robustness of Deep Neural Networks
复制标题
少即是多：剔除训练集以提高深度神经网络的鲁棒性
DOI：
10.1007/978-3-030-01554-1_6
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Chen, Hao
中科院分区：
文献类型：
--
作者：
Liu, Yongshuai;Chen, Jiyu;Chen, Hao
Deep neural networks are vulnerable to adversarial examples. Prior defenses attempted to make deep networks more robust by either changing the network architecture or augmenting the training set with adversarial examples, but both have inherent limitations. Motivated by recent research that shows outliers in the training set have a high negative influence on the trained model, we studied the relationship between model robustness and the quality of the training set. We first show that outliers give the model better generalization ability but weaker robustness. Next, we propose an adversarial example detection framework, in which we design two methods for removing outliers from training set to obtain the sanitized model and then detect adversarial example by calculating the difference of outputs between the original and the sanitized model. We evaluated the framework on both MNIST and SVHN. Based on the difference measured by Kullback-Leibler divergence, we could detect adversarial examples with accuracy between 94.67% to 99.89%.
