2019/02/27 by Zhenyu Duan, Duan, Zhenyu, Martin Renqiang Min +9 · 1 citation
Computer Science · #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
paper · pdf · doi:10.48550/arxiv.1902.11134
openalex publication_date 2019/02/27 · openalex created_date 2019/03/02 · openalex updated_date 2026/07/28
In spite of achieving revolutionary successes in machine learning, deep convolutional neural networks have been recently found to be vulnerable to adversarial attacks and difficult to generalize to novel test images with reasonably large geometric transformations. Inspired by a recent neuroscience discovery revealing that primate brain employs disentangled shape and appearance representations for object recognition, we propose a general disentangled deep autoencoding regularization framework that can be easily applied to any deep embedding based classification model for improving the robustness of deep neural networks. Our framework effectively learns disentangled appearance code and geometric code for robust image classification, which is the first disentangling based method defending against adversarial attacks and complementary to standard defense methods. Extensive experiments on several benchmark datasets show that, our proposed regularization framework leveraging disentangled embedding significantly outperforms traditional unregularized convolutional neural networks for image classification on robustness against adversarial attacks and generalization to novel test data.