DeepAI AI Chat
Log In Sign Up

Appending Adversarial Frames for Universal Video Attack

by   Zhikai Chen, et al.
HUAWEI Technologies Co., Ltd.
Xi'an Jiaotong University

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.


page 1

page 6

page 7

page 12


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

Widely deployed deep neural network (DNN) models have been proven to be ...

Sparse Adversarial Perturbations for Videos

Although adversarial samples of deep neural networks (DNNs) have been in...

Universal Adversarial Audio Perturbations

We demonstrate the existence of universal adversarial perturbations, whi...

Motion-Excited Sampler: Video Adversarial Attack with Sparked Prior

Deep neural networks are known to be susceptible to adversarial noise, w...

Adversarially Robust Frame Sampling with Bounded Irregularities

In recent years, video analysis tools for automatically extracting meani...

PAT: Pseudo-Adversarial Training For Detecting Adversarial Videos

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

NetFlick: Adversarial Flickering Attacks on Deep Learning Based Video Compression

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