Natural language video localization (NLVL) is an important task in the vision-language understanding area, which calls for an in-depth understanding of not only computer vision and natural language side alone, but more importantly the interplay between both sides. Adversarial vulnerability has been well-recognized as a critical security issue of deep neural network models, which requires prudent investigation. Despite its extensive yet separated studies in video and language tasks, current understanding of the adversarial robustness in vision-language joint tasks like NLVL is less developed. This paper therefore aims to comprehensively investigate the adversarial robustness of NLVL models by examining three facets of vulnerabilities from both attack and defense aspects. To achieve the attack goal, we propose a new adversarial attack paradigm called synonymous sentences-aware adversarial attack on NLVL (SNEAK), which captures the cross-modality interplay between the vision and language sides.
@article{arxiv.2112.04154,
title = {SNEAK: Synonymous Sentences-Aware Adversarial Attack on Natural Language Video Localization},
author = {Wenbo Gou and Wen Shi and Jian Lou and Lijie Huang and Pan Zhou and Ruixuan Li},
journal= {arXiv preprint arXiv:2112.04154},
year = {2021}
}