2022/04/19 by Mirazul Haque, Haque, Mirazul, Christof J. Budnik +3
Computer Science · #Advanced Neural Network Applications #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #cs.CV #cs.LG
paper · pdf · doi:10.48550/arxiv.2204.08623
arxiv created 2022/04/19 · openalex publication_date 2022/04/19 · arxiv updated 2022/04/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Because of the increasing accuracy of Deep Neural Networks (DNNs) on different tasks, a lot of real times systems are utilizing DNNs. These DNNs are vulnerable to adversarial perturbations and corruptions. Specifically, natural corruptions like fog, blur, contrast etc can affect the prediction of DNN in an autonomous vehicle. In real time, these corruptions are needed to be detected and also the corrupted inputs are needed to be de-noised to be predicted correctly. In this work, we propose CorrGAN approach, which can generate benign input when a corrupted input is provided. In this framework, we train Generative Adversarial Network (GAN) with novel intermediate output-based loss function. The GAN can denoise the corrupted input and generate benign input. Through experimentation, we show that up to 75.2% of the corrupted misclassified inputs can be classified correctly by DNN using CorrGAN.