ECCV 2020 Workshop on Adversarial Robustness in the Real World

Computer vision systems nowadays have advanced performance but research in adversarial machine learning also shows that they are not as robust as the human vision system. The existence of real-world adversarial examples, created under scenarios such as partial occlusion or previously unseen environments, provides opportunities for understanding and improving computer vision systems.

In this workshop, we seek to utilize adversarial machine learning in real-world environments to identify and understand the limitations of current computer vision systems, as well as to improve their performance. For more details please visit Adversarial Robustness in the Real World.