CVPR 2021 Tutorial on

Adversarial Machine Learning in Computer Vision

09:55 am - 5:30 pm ET (GMT-4), June 19, 2021

[Video Recording]


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.


09:55 - 10:00         Opening Remark

10:00 - 10:35         Talk 1: Xinyun Chen - Adversarial Attacks in Computer Vision: An Overview   [SLIDES]

10:35 - 11:10         Talk 2: Shao-Yuan Lo & Vishal Patel - Adversarial Attacks & Defenses in Video   [SLIDES]

11:10 - 11:45         Talk 3: Matthias Niessner - Deepfakes Creation and Detection   [SLIDES]

11:45 - 12:20         Talk 4: Chaowei Xiao - 3D Adversarial Attacks   [SLIDES]

12:20 - 14:00         Lunch Break

14:00 - 14:35         Talk 5: Tom Goldstein - Poisoning Attacks on Computer Vision Models   [SLIDES]

14:35 - 15:10         Talk 6: Judy Hoffman - Detecting Reliable Instances for Learning   [SLIDES]

15:10 - 15:45         Talk 7: Cihang Xie - Adversarial Examples Improve Image Recognition   [SLIDES]

15:45 - 16:20         Talk 8: Raquel Urtasun - Adversarial Attacks and Robustness for Self-driving

16:20 - 16:55         Talk 9: Luca Carlone - Certifiably Robust Geometric Perception for Robots and Autonomous Vehicles   [SLIDES]

16:55 - 17:30         Talk 10: Alan Yuille - Robust Object Detection Under Occlusion with Compositional Generative Networks   [SLIDES]

Organizing Committee

Please contact Cihang Xie or Xinyun Chen if you have questions. The webpage template is by the courtesy of ICCV 2019 Tutorial on Interpretable Machine Learning for Computer Vision.