Jaechul (Harry) Roh

81172002_557371371774825_3245898086832468713_n.jpg
  • Facebook
  • LinkedIn

I'm a final year undergraduate student in computer engineering at Hong Kong University of Science and Technology (HKUST) in the School of Engineering. My research interests rely on Trustworthy AI and robustness of deep neural networks. Especially, I am fascinated by both adversarial attack as well as adversarial training to overcome the vulnerability of various machine learning models in wide range of domains. I am also interested in exploring other fields of study such as the relationship between adversarial attack and federated learning, backdoor attacks/defense, fairness, and natural language processing. 

Publications

  • Robust Smart Home Face Recognition under Starving Federated Data 

      Jaechul Roh, Yajun Fang

       International Conference on Universal Village (IEEE UV2022), 2022/09/26        

       [paper] [code] [slides] [video]

       Jaechul Roh, Minhao Cheng, Yajun Fang       

       International Conference on Universal Village (IEEE UV2022)

        2022/09/26

       [paper] [code] [slides] [video]

  • Paper" Impact of Adversarial Training on the Robustness of Deep Neural Networks has been accepted by the ​​2022 IEEE 5th International Conference on Information Systems and Computer Aided Education (ICISCAE). (2022/04/15)

       Jaechul Roh

        [paper[code]