Huimin Zeng
Hello, this is Huimin Zeng (曾惠民 in Chinese)! I am currently a 2nd year Ph.D. student at University of Illinois Urbana-Champaign, advised by Prof. Dong Wang. Prior to that, I graduated with M.Sc. degree in Robotics, Cognition, Intelligence with Distinction from Technische Universität München in 2021. I received my B.Sc. in Robotics and Automation from Tongji University in 2018.
My research interest lies in trustworthy machine learning, NLP and recommender systems.
Selected Publications
On Adversarial Robustness of Demographic Fairness in Face Attribute Recognition
Huimin Zeng, Zhenrui Yue, Yang Zhang, Lanyu Shang, Dong Wang
IJCAI 2023
Manipulating Out-Domain Uncertainty Estimation in Deep Neural Networks via Targeted Clean-Label Poisoning
Huimin Zeng, Zhenrui Yue, Yang Zhang, Lanyu Shang, Dong Wang
CIKM 2023
Manipulating Out-Domain Uncertainty Estimation in Deep Neural Networks via Targeted Clean-Label Poisoning
Huimin Zeng, Zhenrui Yue, Ziyi Kou, Yang Zhang, Lanyu Shang, Dong Wang
KBS 2023
Fairness-aware Training of Face Attribute Classifiers via Adversarial Robustness
Huimin Zeng, Zhenrui Yue, Ziyi Kou, Lanyu Shang, Yang Zhang, Dong Wang
ASONAM 2022
Boosting Demographic Fairness of Face Attribute Classifiers via Latent Adversarial Representations
Huimin Zeng, Zhenrui Yue, Lanyu Shang, Yang Zhang, Dong Wang
BigData 2022
On Attacking Out-Domain Uncertainty Estimation in Deep Neural Networks
Huimin Zeng, Zhenrui Yue, Yang Zhang, Ziyi Kou, Lanyu Shang, Dong Wang
IJCAI 2022
Are adversarial examples created equal? A learnable weighted minimax risk for robustness under non-uniform attacks
Huimin Zeng, Chen Zhu, Tom Goldstein, Furong Huang
AAAI 2021
Full publication list can be found in my google scholar page.
Miscellaneous
Teaching: Computer Networks, Intro to Database, Intro to Deep Learning.