DeepAI AI Chat
Log In Sign Up

Inter-frame Accelerate Attack against Video Interpolation Models

by   Junpei Liao, et al.
University of Electronic Science and Technology of China
The Chinese University of Hong Kong, Shenzhen
NetEase, Inc

Deep learning based video frame interpolation (VIF) method, aiming to synthesis the intermediate frames to enhance video quality, have been highly developed in the past few years. This paper investigates the adversarial robustness of VIF models. We apply adversarial attacks to VIF models and find that the VIF models are very vulnerable to adversarial examples. To improve attack efficiency, we suggest to make full use of the property of video frame interpolation task. The intuition is that the gap between adjacent frames would be small, leading to the corresponding adversarial perturbations being similar as well. Then we propose a novel attack method named Inter-frame Accelerate Attack (IAA) that initializes the perturbation as the perturbation for the previous adjacent frame and reduces the number of attack iterations. It is shown that our method can improve attack efficiency greatly while achieving comparable attack performance with traditional methods. Besides, we also extend our method to video recognition models which are higher level vision tasks and achieves great attack efficiency.


page 3

page 5

page 7

page 8


Just One Moment: Inconspicuous One Frame Attack on Deep Action Recognition

The video-based action recognition task has been extensively studied in ...

Heuristic Black-box Adversarial Attacks on Video Recognition Models

We study the problem of attacking video recognition models in the black-...

Frame Interpolation with Multi-Scale Deep Loss Functions and Generative Adversarial Networks

Frame interpolation attempts to synthesise intermediate frames given one...

Sparse Black-box Video Attack with Reinforcement Learning

Adversarial attacks on video recognition models have been explored recen...

Reinforcement Learning Based Sparse Black-box Adversarial Attack on Video Recognition Models

We explore the black-box adversarial attack on video recognition models....

Applying Tensor Decomposition to image for Robustness against Adversarial Attack

Nowadays the deep learning technology is growing faster and shows dramat...

Deep Iterative Frame Interpolation for Full-frame Video Stabilization

Video stabilization is a fundamental and important technique for higher ...