Deep learning has transformed computer vision in the past few years. As fueled by powerful computational resources and massive amounts of data, deep networks achieve compelling, sometimes even superhuman, performance on a wide range of visual benchmarks. Nonetheless, these success stories come with bitterness---deep networks are extremely vulnerable to adversarial examples. The existence of adversarial examples reveals that the computations performed by the current deep networks are dramatically different from those by human brains, and, on the other hand, provides opportunities for understanding and improving these models.

In this tutorial, we bring together researchers from computer vision, machine learning, security, robotics and cognitive science to jointly craft a series of lectures on covering both the basic backgrounds and the most recent progress of adversarial machine learning, focusing on computer vision.