Bo-Hsu (Hentci) Ke | 柯柏旭

Hello! I'm Bo-Hsu Ke. Some people also call me Hentci—but please don't confuse it with Hentai.

I am pursuing my Master's degree in Computer Science and Engineering at National Yang Ming Chiao Tung University (NYCU), under the supervision of Prof. Wei-Chen Chiu at the Enriched Vision Applications Lab. I am also co-advised by Prof. Yu-Lun Liu at the Computational Photography Lab, specializing in 3D Computer Vision.

I was advised by Prof. Jian-Jhih Kuo during my undergraduate studies before joining NYCU. I earned my Bachelor’s degree in Computer Science from National Chung Cheng University in 2024.

Email  /  CV  /  Scholar  /  Linkedin  /  Github

profile photo

Publications

I'm interested in Computer Vision, Federated Learning, and AI Security. Currently, most of my research is about Novel View Synthesis and AI Security.

Feature Distraction Based Backdoor Defense for Federated Trained Intrusion Detection System
Yu-Wen Chen*, Bo-Hsu Ke*, Yen-Xin Wang, Shih-Heng Lin, Ming-Han Tsai, Bo-Zhong Chen, Jian-Jhih Kuo, Ren-Hung Hwang
IEEE Global Communications Conference, (GLOBECOM), 2024
source code

This paper proposes a novel defense framework called FDDF (Features Distraction Defense Framework) to mitigate trigger backdoor attacks in federated learning-based intrusion detection systems by identifying and eliminating the most significant features that may contain triggers, without interfering with the model training process.

Knowledge Distillation Based Defense for Audio Trigger Backdoor in Federated Learning
Yu-Wen Chen*, Bo-Hsu Ke*, Bo-Zhong Chen*, Si-Rong Chiu, Chun-Wei Tu, Jian-Jhih Kuo
IEEE Global Communications Conference, (GLOBECOM), 2023
source code / paper

We propose the Knowledge Distillation Defense Framework (KDDF) to detect and remove features of the potential triggers during the inference. KDDF utilizes Knowledge Distillation (KD) to train a validation model on each IoT device, which is used to identify suspicious data.

Successive Interference Cancellation Based Defense for Trigger Backdoor in Federated Learning
Yu-Wen Chen*, Bo-Hsu Ke*, Bo-Zhong Chen*, Si-Rong Chiu, Chun-Wei Tu, Jian-Jhih Kuo
IEEE International Conference on Communications, (ICC), 2023
source code / paper

This paper proposes a Successive Interference Cancellation-based Defense Framework (SICDF) to detect and eliminate the trigger during model inference.

Projects

3D-Aware Image Restoration: Leveraging Diffusion Models and Vision Mamba Techniques
NYCU CSIC30153: Deep Learning,
2024-08-31
source code / poster / visual results

Evaluating the effectiveness of various methods (Restormer, fine-tuned diffusion model, and Vision Mamba) in mitigating simulated image artifacts to enhance NeRF and 3DGS performance in novel-view synthesis.

Honors

Bronze Award of The 2022 ICPC Asia Taoyuan Regional Programming Contest

Bronze Award of The 2023 ICPC Asia Taoyuan Regional Programming Contest

Silver Award of The 2023 ICPC Asia Taiwan Online Programming Contest

President's Award in 2023 Spring Semester (Top 1% in the class)

College Student Research Scholarship, National Science and Technology Council, Taiwan (collaborate with Bo-Zhong Chen, 2023)


Stolen from Jon Barron's website.
Last updated Sep 2024.