2021 IEEE International Conference on Image Processing
19-22 September 2021 • Anchorage, Alaska, USA
Imaging Without Borders
| Paper ID | TEC-6.8 | ||
| Paper Title | Overcomplete Representations Against Adversarial Videos | ||
| Authors | Shao-Yuan Lo, Jeya Maria Jose Valanarasu, Vishal Patel, Johns Hopkins University, United States | ||
| Session | TEC-6: Image and Video Processing 2 | ||
| Location | Area G | ||
| Session Time: | Monday, 20 September, 15:30 - 17:00 | ||
| Presentation Time: | Monday, 20 September, 15:30 - 17:00 | ||
| Presentation | Poster | ||
| Topic | Image and Video Processing: Restoration and enhancement | ||
| IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
| Abstract | Adversarial robustness of deep neural networks is an extensively studied problem in the literature and various methods have been proposed to defend against adversarial images. However, only a handful of defense methods have been developed for defending against attacked videos. In this paper, we propose a novel Over-and-Under complete restoration network for Defending against adversarial videos (OUDefend). Most restoration networks adopt an encoder-decoder architecture that first shrinks spatial dimension then expands it back. This approach learns undercomplete representations, which have large receptive fields to collect global information but overlooks local details. On the other hand, overcomplete representations have opposite properties. Hence, OUDefend is designed to balance local and global features by learning those two representations. We attach OUDefend to target video recognition models as a feature restoration block and train the entire network end-to-end. Experimental results show that the defenses focusing on images may be ineffective to videos, while OUDefend enhances robustness against different types of adversarial videos, ranging from additive attacks, multiplicative attacks to physically realizable attacks. Code: https://github.com/shaoyuanlo/OUDefend | ||