TY - GEN
T1 - PAT
T2 - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022
AU - Thakur, Nupur
AU - Li, Baoxin
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Extensive research has demonstrated that deep neural networks (DNNs) are prone to adversarial attacks. Although various defense mechanisms have been proposed for image classification networks, fewer approaches exist for video-based models used in security-sensitive applications like surveillance. In this paper, we propose a novel yet simple algorithm called Pseudo-Adversarial Training (PAT), to detect the adversarial frames in a video without requiring knowledge of the attack. Our approach generates 'transition frames' that capture critical deviation from the original frames and eliminate the components insignificant to the detection task. To avoid the necessity of knowing the attack model, we produce 'pseudo perturbations' to train our detection network. Adversarial video detection is then achieved through the use of the detected frames. Experimental results on UCF-101 and 20BN-Jester datasets show that PAT can detect the adversarial video frames and videos with a high detection rate. We also unveil the potential reasons for the effectiveness of the transition frames and pseudo perturbations through extensive experiments.
AB - Extensive research has demonstrated that deep neural networks (DNNs) are prone to adversarial attacks. Although various defense mechanisms have been proposed for image classification networks, fewer approaches exist for video-based models used in security-sensitive applications like surveillance. In this paper, we propose a novel yet simple algorithm called Pseudo-Adversarial Training (PAT), to detect the adversarial frames in a video without requiring knowledge of the attack. Our approach generates 'transition frames' that capture critical deviation from the original frames and eliminate the components insignificant to the detection task. To avoid the necessity of knowing the attack model, we produce 'pseudo perturbations' to train our detection network. Adversarial video detection is then achieved through the use of the detected frames. Experimental results on UCF-101 and 20BN-Jester datasets show that PAT can detect the adversarial video frames and videos with a high detection rate. We also unveil the potential reasons for the effectiveness of the transition frames and pseudo perturbations through extensive experiments.
UR - http://www.scopus.com/inward/record.url?scp=85137794751&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85137794751&partnerID=8YFLogxK
U2 - 10.1109/CVPRW56347.2022.00024
DO - 10.1109/CVPRW56347.2022.00024
M3 - Conference contribution
AN - SCOPUS:85137794751
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 130
EP - 137
BT - Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022
PB - IEEE Computer Society
Y2 - 19 June 2022 through 20 June 2022
ER -