Bo-Han Kung

龔柏翰

I am a Ph.D. candidate in the Department of Computer Science and Information Engineering at National Taiwan University, currently conducting research in the Artificial Intelligence Security Lab (AIS Lab) under Prof. Shang-Tse Chen.

Before joining AIS Lab, I worked full-time as a Research Assistant at AiiuLab, Academia Sinica, under Prof. Jun-Cheng Chen, where I focused on improving the robustness of computer vision systems.

My research interests have since expanded to encompass both theoretical and applied security aspects of machine learning.


Education

2021 - present
Ph.D. student in Computer Science and Information Engineering
National Taiwan University (NTU), Taipei, Taiwan

2018 - 2020
M.S. in Biomedical Electronics and Bioinformatics
National Taiwan University (NTU), Taipei, Taiwan

2014 - 2018
B.S. in Mechanical Engineering
National Taiwan University (NTU), Taipei, Taiwan

Publications

ICML 2025

Enhancing Certified Robustness via Block Reflector Orthogonal Layers and Logit Annealing Loss
Bo-Han Lai*, Pin-Han Huang*, Bo-Han Kung* and Shang-Tse Chen
International Conference on Machine Learning (ICML) (spotlight)

AAAI 2024

Towards Large Certified Radius in Randomized Smoothing Using Quasiconcave Optimization
Bo-Han Kung and Shang-Tse Chen
Proceedings of the AAAI Conference on Artificial Intelligence, 2024, pp. 21285-21293

ICASSP 2022

Clipcam: A simple baseline for zero-shot text-guided object and action localization
Hsuan-An Hsia, Che-Hsien Lin, Bo-Han Kung, Jhao-Ting Chen, Daniel Stanley Tan, Jun-Cheng Chen, Kai-Lung Hua
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4453-4457

ICCV 2021

Naturalistic Physical Adversarial Patch for Object Detectors
Yu-Chih-Tuan Hu, Bo-Han Kung, Daniel Stanley Tan, Jun-Cheng Chen, Kai-Lung Hua, and Wen-Huang Cheng
Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 7848-7857
Github

CVPR 2021

Class-Aware Robust Adversarial Training for Object Detection
Pin-Chun Chen, Bo-Han Kung, and Jun-Cheng Chen
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 10420-10429

ICIP 2021

Squeeze and Reconstruct: Improved Practical Adversarial Defense using Paired Image Compression and Reconstruction
Bo-Han Kung, Pin-Chun Chen, Yu-Cheng Liu, and Jun-Cheng Chen
2021 IEEE International Conference on Image Processing (ICIP), 2021, pp. 849-853

JBHI 2020

An Efficient ECG Classification System Using Resource-Saving Architecture and Random Forest
Bo-Han Kung, Po-Yuan Hu, Chiu-Chang Huang, Cheng-Che Lee, Chia-Yu Yao, and Chieh-Hsiung Kuan
IEEE Journal of Biomedical and Health Informatics, vol. 25, no. 6, pp. 1904-1914, June 2021

CLEO 2020

Baseline Correction and Denoising of Raman Spectra by Deep Residual CNN
Bo-Han Kung, Chiu-Chang Huang, Po-Yuan Hu, Shao-yu Lo, Cheng-Che Lee, Chia-Yu Yao, and Chieh-Hsiung Kuan
2020 Conference on Lasers and Electro-Optics (CLEO), 2020

Experience

2022.02 - 2025.06

Teaching Assistant,
Department of Computer Science and Information Engineering, National Taiwan University.
Course: Introduction to Medical Informatics

2021.09 - 2022.01

Teaching Assistant,
Department of Computer Science and Information Engineering, National Taiwan University.
Course: Digital Signal Processing


2020.07 - 2021.08

Research Assistant (Full-time, 13 months),
Research Center for Information Technology Innovation, Academia Sinica.
Advised by Prof. Jun-Cheng Chen.
Research: Computer Vision, Neural Networks Robustness.


2020.02 - 2020.06

Teaching Assistant,
Department of Electrical Engineering, National Taiwan University.
Course: Probability and Statistics


2019.09 - 2020.01

Teaching Assistant,
Department of Electrical Engineering, National Taiwan University.
Course: Differential Equation


2019.02 - 2019.06

Teaching Assistant,
Department of Electrical Engineering, National Taiwan University.
Course: Electronic Circuits


2018.09 - 2019.01

Teaching Assistant,
Department of Electrical Engineering, National Taiwan University.
Course: Differential Equation