Over-the-Air Adversarial Flickering Attacks against Video Recognition Networks
Deep neural networks for video classification, just like image classification networks, may be subjected to adversarial manipulation. The main difference between image classifiers and video classifiers is that the latter usually use temporal information contained within the video. In this work we present a manipulation scheme for fooling video classifiers by introducing a flickering temporal perturbation that in some cases may be unnoticeable by human observers and is implementable in the real world. After demonstrating the manipulation of action classification of single videos, we generalize the procedure to make universal adversarial perturbation, achieving high fooling ratio. In addition, we generalize the universal perturbation and produce a temporal-invariant perturbation, which can be applied to the video without synchronizing the perturbation to the input. The attack was implemented on several target models and the transferability of the attack was demonstrated. These properties allow us to bridge the gap between simulated environment and real-world application, as will be demonstrated in this paper for the first time for an over-the-air flickering attack.
Code (1)
Tasks
Action ClassificationClassificationGeneral Classificationimage-classificationImage ClassificationOptical Flow EstimationVideo ClassificationVideo RecognitionSimilar Papers 제목 키워드 기반
NetFlick: Adversarial Flickering Attacks on Deep Learning Based Video Compression
Video compression plays a significant role in IoT devices for the efficient transport of visual data while satisfying all underlying bandwidth constraints. Deep learning-based video compression methods are rapidly replac…
Deep LearningVideo ClassificationVideo CompressionMultAV: Multiplicative Adversarial Videos
The majority of adversarial machine learning research focuses on additive attacks, which add adversarial perturbation to input data. On the other hand, unlike image recognition problems, only a handful of attack approach…
Adversarial AttackVideo RecognitionOvercomplete Representations Against Adversarial Videos
Adversarial robustness of deep neural networks is an extensively studied problem in the literature and various methods have been proposed to defend against adversarial images. However, only a handful of defense methods h…
Adversarial RobustnessDecoderVideo RecognitionTemporally Consistent Semantic Video Editing
Generative adversarial networks (GANs) have demonstrated impressive image generation quality and semantic editing capability of real images, e.g., changing object classes, modifying attributes, or transferring styles. Ho…
Image GenerationVideo EditingFMVP: Masked Flow Matching for Adversarial Video Purification
Video recognition models remain vulnerable to adversarial attacks, while existing diffusion-based purification methods suffer from inefficient sampling and curved trajectories. Directly regressing clean videos from adver…