QEBB: A Query-Efficient Black-Box Adversarial Attack on Video Recognition Models Based on Unsupervised Key Frame Selection

Kimia Haghjooei, Mansoor Rezghi

2024

Abstract

Despite the success of deep learning models, they remain vulnerable to adversarial attacks introducing slight perturbations to inputs, resulting in adversarial examples. Black-box attacks, where model details are hidden from the attacker, gain attention for their real-world applications. Although studying adversarial attacks on video models is crucial due to their surveillance importance and security applications, most works on adversarial examples mainly focus on images, and videos are rarely studied since attacking videos is more challenging. Recent black-box video attacks involve selecting key frames to reduce video’s dimensionality. This addresses the high costs of attacking the entire video but may require numerous queries, making the attack noticeable. Our work introduces QEBB, a query-efficient black-box video attack. We employ an unsupervised key frame selection method to choose frames with vital representative information. Using saliency maps, we focus on key frame salient regions. QEBB successfully attacks UCF-101 and HMDB-51 datasets with 100% success and reducing query numbers by nearly 90% in comparison to state-of-the-art methods.

Paper Citation

in Harvard Style

Haghjooei K. and Rezghi M. (2024). QEBB: A Query-Efficient Black-Box Adversarial Attack on Video Recognition Models Based on Unsupervised Key Frame Selection. In Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM; ISBN 978-989-758-684-2, SciTePress, pages 288-295. DOI: 10.5220/0012359900003654

in Bibtex Style

@conference{icpram24,
author={Kimia Haghjooei and Mansoor Rezghi},
title={QEBB: A Query-Efficient Black-Box Adversarial Attack on Video Recognition Models Based on Unsupervised Key Frame Selection},
booktitle={Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM},
year={2024},
pages={288-295},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012359900003654},
isbn={978-989-758-684-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM
TI - QEBB: A Query-Efficient Black-Box Adversarial Attack on Video Recognition Models Based on Unsupervised Key Frame Selection
SN - 978-989-758-684-2
AU - Haghjooei K.
AU - Rezghi M.
PY - 2024
SP - 288
EP - 295
DO - 10.5220/0012359900003654
PB - SciTePress