.png){kind=icon}
返回
DARE: Deceiving Audio-Visual speech Recognition model
.png){kind=icon}
PRE
AI
DOI：10.1016/j.knosys.2021.107503.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Audio-Visual speech recognition (AVSR) is an effective way to predict text corresponding to the spoken words using both audio and face videos, even in a noisy environment. These models find extensive applications in various fields like assisting hearing-impaired, biometric verification and speaker verification. Adversarial examples are created by adding imperceptible perturbations to the original input resulting in an incorrect classification by the deep learning models. Attacking an AVSR model is quite challenging, as both audio and visual modalities complement each other. Moreover, the correlation between audio and video features decreases while crafting an adversarial example, which can be used for detecting the adversarial example. We propose an end-to-end targeted attack, Deceiving Audio-visual speech Recognition model (DARE), which successfully performs an imperceptible adversarial attack while remaining undetected by the existing synchronisation-based detection network, SyncNet. To this end, we are the first to perform an adversarial attack that fools the AVSR model and SyncNet simultaneously. Experimental results on the publicly available dataset using state-of-the-art AVSR model reveal that the proposed attack can successfully deceive the AVSR model while remaining undetected. Furthermore, our DARE attack circumvents the well-known defences while maintaining a 100% targeted attack success rate. (C) 2021 Elsevier B.V. All rights reserved.
Keyword:
Audio-Visual Speech Recognition
Adversarial attacks
Cross-modality
Detection network
期刊
K
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
.png){kind=icon}
分享收藏Improving adversarial robustness of deep neural networks by using semantic information利用语义信息提高深度神经网络的对抗鲁棒性
OAAI
OAAI分享收藏分享收藏Automatic classification of personal video recordings based on audiovisual features基于视听特征的个人录像自动分类
PREAI
分享收藏
查看更多内容