Exploring the Interplay of Interpretability and Robustness in Deep Neural Networks: A Saliency-guided Approach

arXiv:2405.06278v1 Announce Type: cross
Abstract: Adversarial attacks pose a significant challenge to deploying deep learning models in safety-critical applications. Maintaining model robustness while ensuring interpretability is vital for fostering trust and comprehension in these models. This study investigates the impact of Saliency-guided Training (SGT) on model robustness, a technique aimed at improving the clarity of saliency maps to deepen understanding of the model's decision-making process. Experiments were conducted on standard benchmark datasets using various deep learning architectures trained with and …

adversarial adversarial attacks applications arxiv attacks challenge critical cs.cr cs.cv deep learning impact networks neural networks robustness safety safety-critical study training trust