MUFIA Frequency-Based Vulnerability Analysis of Deep Learning Models against Image Corruptions A Little Fog for a Large Turn Generating realistic foggy conditions to test autonomous navigation systems Latent Adversarial Training Analyzing the weaknesses of adversarially trained neural networks and introducing Latent Adversarial Training (LAT) for improved robustness. EREN Enhancing deep learning robustness through image pre-processing CLAD A Contrastive Learning based Approach for Background Debiasing
