Wang.Jian(王剑)

Jian Wang is a DPhil( start at August 2021), at Cyber Security, Computer Science(SCSE), NanYang Technological University, Singapore, advised by Prof Li.Yi and Prof Liu.Yang where he work in Security and eXplainable on Machine Learning.

Email.edu  /  CV  /  Biography  /  Google Scholar  /  Twitter

profile photo
Bio

Jian Wang was a research assistant in Computer Science and Engineering at Nanyang Technological University since 2019. Previously, he was a researcher at Xiaomi AI Lab and an engineer who worked at 58.Inc and Baidu.Inc.

Jian Wang received a B.A. in Software Engineering from Tianjin University, China.

Jian Wang's research interests include machine learning algorithms and theory, adversarial methods for privacy data, and their applications. His specific interest is in Security Analysis, Trending Analysis, and Privacy Protection.
He is now heavily engaged in robust AI by creating high-realism adversarial attacks/defence such as trace-based repair for defence, adversarial motion blur for attacking, facial-skew adversarial for deepfake detection, etc.

Representative papers are highlighted.

Research

prl

Automatic RNN Repair via Model-based Analysis
Xiaofei Xie, Wenbo Guo, Lei Ma, Wei Le, Jian Wang, Linjun Zhou, Yang Liu, Xinyu Xing
International Conference on Machine Learning (ICML), 2021
PDF / bibtex / Poster

We propose a lightweight model-based influence analysis, to help understand and repair incorrect behaviors of an RNN. Specifically, we first build an automaton to enable high-quality feature extraction and to characterize the stateful and statistical behaviors of an RNN over all the training data.
prl

Watch out! Motion is Blurring the Vision of Your Deep Neural Networks
Qing Guo, Felix Juefei-Xu, Xiaofei Xie, Lei Ma, Jian Wang, Bing Yu, Wei Feng, Yang Liu
Advances in Neural Information Processing Systems (NeurIPS), 2020
arxiv / bibtex


We newly identify an attacking method termed motion-based adversarial blur attack (ABBA) that can generate visually natural motion-blurred adversarial examples. -- by Xu.Juefei

prl

FakeSpotter: A Simple yet Robust Baseline for Spotting AI-Synthesized Fake Faces
Run Wang, Felix Juefei-Xu, Lei Ma, Xiaofei Xie, Yihao Huang, Jian Wang, Yang Liu
International Joint Conference on Artificial Intelligence (IJCAI), 2020
arxiv / bibtex

Media Coverage: Synced Review


Monitoring neuron behavior can serve as an asset in detecting AI-synthesized fake faces since layer-by-layer neuron activation patterns may capture more subtle features that are important for the fake detector. -- by Xu.Juefei

Engineering
cs188
Xiaomi Group
Xiaomi AI lab, Beijing, China
2017-2019
58.Inc
BackEnd Engineer(Nginx based gateway), 58 Group. Beijing, China
2011-2017
cs188

Baidu Group
Baidu Data Engineer (Intern), Beijing, China
2011

I forked this source code from jonbarron and xujuefei. Also, consider using Leonid Keselman's Jekyll fork of this page.