Appending Adversarial Frames for Universal Video Attack

12/10/2019
by   Zhikai Chen, et al.
34

There have been many efforts in attacking image classification models with adversarial perturbations, but the same topic on video classification has not yet been thoroughly studied. This paper presents a novel idea of video-based attack, which appends a few dummy frames (e.g., containing the texts of `thanks for watching') to a video clip and then adds adversarial perturbations only on these new frames. Our approach enjoys three major benefits, namely, a high success rate, a low perceptibility, and a strong ability in transferring across different networks. These benefits mostly come from the common dummy frame which pushes all samples towards the boundary of classification. On the other hand, such attacks are easily to be concealed since most people would not notice the abnormality behind the perturbed video clips. We perform experiments on two popular datasets with six state-of-the-art video classification models, and demonstrate the effectiveness of our approach in the scenario of universal video attacks.

READ FULL TEXT

page 1

page 6

page 7

page 12

research
07/09/2021

Universal 3-Dimensional Perturbations for Black-Box Attacks on Video Recognition Systems

Widely deployed deep neural network (DNN) models have been proven to be ...
research
03/07/2018

Sparse Adversarial Perturbations for Videos

Although adversarial samples of deep neural networks (DNNs) have been in...
research
08/08/2019

Universal Adversarial Audio Perturbations

We demonstrate the existence of universal adversarial perturbations, whi...
research
03/17/2020

Motion-Excited Sampler: Video Adversarial Attack with Sparked Prior

Deep neural networks are known to be susceptible to adversarial noise, w...
research
02/04/2020

Adversarially Robust Frame Sampling with Bounded Irregularities

In recent years, video analysis tools for automatically extracting meani...
research
09/13/2021

PAT: Pseudo-Adversarial Training For Detecting Adversarial Videos

Extensive research has demonstrated that deep neural networks (DNNs) are...
research
04/04/2023

NetFlick: Adversarial Flickering Attacks on Deep Learning Based Video Compression

Video compression plays a significant role in IoT devices for the effici...

Please sign up or login with your details

Forgot password? Click here to reset