2022/02/05 by Eashan Adhikarla, Dan Luo, Adhikarla, Eashan +3
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)
paper · pdf · doi:10.48550/arxiv.2202.02595
openalex publication_date 2022/02/05 · openalex created_date 2022/05/05 · openalex updated_date 2026/07/28
Many deep neural networks are susceptible to minute perturbations of images that have been carefully crafted to cause misclassification. Ideally, a robust classifier would be immune to small variations in input images, and a number of defensive approaches have been created as a result. One method would be to discern a latent representation which could ignore small changes to the input. However, typical autoencoders easily mingle inter-class latent representations when there are strong similarities between classes, making it harder for a decoder to accurately project the image back to the original high-dimensional space. We propose a novel framework, Memory Defense, an augmented classifier with a memory-masking autoencoder to counter this challenge. By masking other classes, the autoencoder learns class-specific independent latent representations. We test the model's robustness against four widely used attacks. Experiments on the Fashion-MNIST & CIFAR-10 datasets demonstrate the superiority of our model. We make available our source code at GitHub repository: https://github.com/eashanadhikarla/MemDefense