13 Papers
26 Citations
Kun Wan is an academic researcher from University of California, Santa Barbara. The author has contributed to research in topics: Convolutional neural network & Computer science. The author has an hindex of 3, co-authored 12 publications.
Chat about Author
Papers
Weighted-Sampling Audio Adversarial Example Attack.
Xiaolei Liu,Kun Wan,Yufei Ding,Xiaosong Zhang,Qingxin Zhu +4 more
- 03 Apr 2020
TL;DR: Weighted-sampling audio adversarial examples are proposed, focusing on the numbers and the weights of distortion to reinforce the attack, and a denoising method in the loss function is applied to make the adversarial attack more imperceptible.
Domain-adversarial multi-task framework for novel therapeutic property prediction of compounds
Lingwei Xie,Song He,Zhongnan Zhang,Kunhui Lin,Xiaochen Bo,Shu Yang,Boyuan Feng,Kun Wan,Kang Yang,Jie Yang,Yufei Ding +10 more
TL;DR: A novel domain-adversarial multi-task framework for integrating shared knowledge from multiple domains that first uses an adversarial strategy to learn target representations and then models nonlinear dependency among several domains.
Compiler-Based Efficient CNN Model Construction for 5G Edge Devices
TL;DR: Experimental results show that models composed of the sparse kernel designs searched by the proposed search scheme can beat state-of-the-art networks such as ResNets in terms of the accuracy and the efficiency.
9
•Posted Content
Weighted-Sampling Audio Adversarial Example Attack
TL;DR: In this article, a weighted sampling method was proposed to generate audio adversarial examples with low noise and high audio robustness at the minute time-consuming level, and a denoising method was applied in the loss function to make the adversarial attack more imperceptible.
6
•Posted Content
Towards Weighted-Sampling Audio Adversarial Example Attack.
TL;DR: Experiments show that this method is the first in the field to generate audio adversarial examples with low noise and high audio robustness at the minute time-consuming level.
6