.png){kind=icon}
返回
Towards the transferable audio adversarial attack via ensemble methods
.png){kind=icon}
OA
AI
DOI：10.1186/s42400-023-00175-8.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In recent years, deep learning (DL) models have achieved significant progress in many domains, such as autonomous driving, facial recognition, and speech recognition. However, the vulnerability of deep learning models to adversarial attacks has raised serious concerns in the community because of their insufficient robustness and generalization. Also, transferable attacks have become a prominent method for black-box attacks. In this work, we explore the potential factors that impact adversarial examples (AEs) transferability in DL-based speech recognition. We also discuss the vulnerability of different DL systems and the irregular nature of decision boundaries. Our results show a remarkable difference in the transferability of AEs between speech and images, with the data relevance being low in images but opposite in speech recognition. Motivated by dropout-based ensemble approaches, we propose random gradient ensembles and dynamic gradient-weighted ensembles, and we evaluate the impact of ensembles on the transferability of AEs. The results show that the AEs created by both approaches are valid for transfer to the black box API.
Keyword:
Adversarial attacks
Dynamic gradient weighting
Transferability
Ensemble methods
期刊
C
IF:
3.7
论文数:
591
被引数:
1.0K
机构
引用论文
.png){kind=icon}
Welding characteristics of aluminum, copper, nickel and aluminum alloy with alumina coating using ultrasonic complex vibration welding equipments铝、铜、镍及铝合金氧化铝涂层超声复合振动焊接特性研究
PREAI
分享收藏Cloning and expression of various staphylococcal genes encoding urease inStaphylococcus carnosus
PREAI
分享收藏
查看更多内容