Adversarial Attacks on Deep Learning-based Video Compression and Classification Systems

03/18/2022
by   Jung-Woo Chang, et al.
0

Video compression plays a crucial role in enabling video streaming and classification systems and maximizing the end-user quality of experience (QoE) at a given bandwidth budget. In this paper, we conduct the first systematic study for adversarial attacks on deep learning based video compression and downstream classification systems. We propose an adaptive adversarial attack that can manipulate the Rate-Distortion (R-D) relationship of a video compression model to achieve two adversarial goals: (1) increasing the network bandwidth or (2) degrading the video quality for end-users. We further devise novel objectives for targeted and untargeted attacks to a downstream video classification service. Finally, we design an input-invariant perturbation that universally disrupts video compression and classification systems in real time. Unlike previously proposed attacks on video classification, our adversarial perturbations are the first to withstand compression. We empirically show the resilience of our attacks against various defenses, i.e., adversarial training, video denoising, and JPEG compression. Our extensive experimental results on various video datasets demonstrate the effectiveness of our attacks. Our video quality and bandwidth attacks deteriorate peak signal-to-noise ratio by up to 5.4dB and the bit-rate by up to 2.4 times on the standard video compression datasets while achieving over 90 classifier.

READ FULL TEXT

page 9

page 17

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...
research
08/30/2023

Deep Video Codec Control

Lossy video compression is commonly used when transmitting and storing v...
research
05/26/2022

Denial-of-Service Attacks on Learned Image Compression

Deep learning techniques have shown promising results in image compressi...
research
02/28/2021

Adversarial Information Bottleneck

The information bottleneck (IB) principle has been adopted to explain de...
research
07/07/2022

Robust Watermarking for Video Forgery Detection with Improved Imperceptibility and Robustness

Videos are prone to tampering attacks that alter the meaning and deceive...
research
02/28/2023

Backdoor Attacks Against Deep Image Compression via Adaptive Frequency Trigger

Recent deep-learning-based compression methods have achieved superior pe...

Please sign up or login with your details

Forgot password? Click here to reset