Evaluating Effectiveness of Adversarial Examples on State of Art License Plate Recognition Models
Kanishk Rana, Rahul Madaan · 2020
Deep learning takes advantage of large datasets and computationally efficient training algorithms to outperform other approaches at various machine learning tasks. However, DNNs are vulnerable to adversarial examples due to imperfections in the training phase. In this work, we generate some adversarial examples to test their effectiveness against the state-of-the-art License Plate Recognition (LPR) models.