activity
20202023
most citedBackdoor Pre-trained Models Can Transfer to All

76 citations · 84 across the 3 of their papers we have counts for

collaborators

5 papers

cs.SD2023

AdvSV: An Over-the-Air Adversarial Attack Dataset for Speaker Verification

Li Wang, Jiaqi Li, Yuhao Luo +7

It is known that deep neural networks are vulnerable to adversarial attacks. Although Automatic Speaker Verification (ASV) built on top of deep neural networks exhibits robust perf…

cs.CL202176 cited

Backdoor Pre-trained Models Can Transfer to All

Lujia Shen, Shouling Ji, Xuhong Zhang +6

Pre-trained general-purpose language models have been a dominating component in enabling real-world natural language processing (NLP) applications. However, a pre-trained model wit…

cs.LG20218 cited

Thief, Beware of What Get You There: Towards Understanding Model Extraction Attack

Xinyi Zhang, Chengfang Fang, Jie Shi

Model extraction increasingly attracts research attentions as keeping commercial AI models private can retain a competitive advantage. In some scenarios, AI models are trained prop…

cs.CV2021

A-FMI: Learning Attributions from Deep Networks via Feature Map Importance

An Zhang, Xiang Wang, Chengfang Fang +3

Gradient-based attribution methods can aid in the understanding of convolutional neural networks (CNNs). However, the redundancy of attribution features and the gradient saturation…

cs.LG2020

Where Does the Robustness Come from? A Study of the Transformation-based Ensemble Defence

Chang Liao, Yao Cheng, Chengfang Fang +1

This paper aims to provide a thorough study on the effectiveness of the transformation-based ensemble defence for image classification and its reasons. It has been empirically show…