Chih-Hsun
Lin
- pkevawin334@gmail.com
Bio: Chih-Hsun Lin is currently pursuing a Ph.D. degree with the Department of Computer Science, at National Yang Ming Chiao Tung University, Hsinchu, Taiwan. His research interests include neural network security and data privacy.
Experience
Period
Sep 2020 - Present
Sep 2016 - Jun 2020
Sep 2008 - Jun 2012
Education
Doctor of Philosophy/Institute of Computer Science and Engineering/National Yang Ming Chiao Tung University
Master/Department of Computer Science and Engineering/National Chung Hsing University
Bachelor/Department of Applied Mathematics/National Chung Hsing University
Journal
[1] Chih-Hsun Lin, Chia-Yi Hsu, Chia-Mu Yu, Cao Yang, and Chun-Ying Huang. DPAF: Image Synthesis via Differentially Private Aggregation in Forward Phase. IEEE Internet of Things Journal, 2024.
[2] Chih-Hsun Lin, Chia-Mu Yu, and Chun-Ying Huang. DPView:Differentially Private Data Synthesis through Domain Size Information. IEEE Internet of Things Journal, 2022.
[2] Chih-Hsun Lin, Chia-Mu Yu, and Chun-Ying Huang. DPView:Differentially Private Data Synthesis through Domain Size Information. IEEE Internet of Things Journal, 2022.
Conference
[1] I-Jung Hsu, Chih-Hsun Lin, Chia-Mu Yu, Sy-Yen Kuo, and Chun-Ying Huang. Poisoning Attacks to Local Differential Privacy Protocols for Trajectory Data. ACM ASIA CCS, 2025. (Under Review)
[2] Chia-Yi Hsu, Jia-You Chen, Yu-Lin Tsai, Chih-Hsun Lin, Pin-Yu Chen, Chia-Mu Yu, and Chun-Ying Huang. VP-NTK: Exploring the Benefits of Visual Prompting in Differentially Private Data Synthesis. IEEE ICASSP, 2025. (Under Review)
[3] Chia-Yi Hsu, Yu-Lin Tsai, Yu Zhe, Yan-Lun Chen, Chih-Hsun Lin, Chia-Mu Yu, Yang Zhang, Chun-Ying Huang, and Jun Sakuma. BadTV: Unveiling Backdoor Threats in Third-Party Task Vectors. USENIX, 2025. (Under Review)
[4] Chia-Yi Hsu, Yu-Lin Tsai, Chih-Hsun Lin, Pin-Yu Chen, Chia-Mu Yu, and Chun-Ying Huang. Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models. NeurIPS, 2024.
[5] Yu-Lin Tsai, Chia-Yi Hsu, Chulin Xie, Chih-Hsun Lin, Jia-You Chen, Bo Li, Pin-Yu Chen, Chia-Mu Yu, and Chun-Ying Huang. Ring-A-Bell! How Reliable are Concept Removal Methods For Diffusion Models?. ICLR, 2024.
[6] Chih-Hsun Lin and Chia-Mu Yu. Privacy-Preserving Record Linkage via Bilinear Pairing Approach. IEEE ICCE-TW, 2018.
[2] Chia-Yi Hsu, Jia-You Chen, Yu-Lin Tsai, Chih-Hsun Lin, Pin-Yu Chen, Chia-Mu Yu, and Chun-Ying Huang. VP-NTK: Exploring the Benefits of Visual Prompting in Differentially Private Data Synthesis. IEEE ICASSP, 2025. (Under Review)
[3] Chia-Yi Hsu, Yu-Lin Tsai, Yu Zhe, Yan-Lun Chen, Chih-Hsun Lin, Chia-Mu Yu, Yang Zhang, Chun-Ying Huang, and Jun Sakuma. BadTV: Unveiling Backdoor Threats in Third-Party Task Vectors. USENIX, 2025. (Under Review)
[4] Chia-Yi Hsu, Yu-Lin Tsai, Chih-Hsun Lin, Pin-Yu Chen, Chia-Mu Yu, and Chun-Ying Huang. Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models. NeurIPS, 2024.
[5] Yu-Lin Tsai, Chia-Yi Hsu, Chulin Xie, Chih-Hsun Lin, Jia-You Chen, Bo Li, Pin-Yu Chen, Chia-Mu Yu, and Chun-Ying Huang. Ring-A-Bell! How Reliable are Concept Removal Methods For Diffusion Models?. ICLR, 2024.
[6] Chih-Hsun Lin and Chia-Mu Yu. Privacy-Preserving Record Linkage via Bilinear Pairing Approach. IEEE ICCE-TW, 2018.
Skills
- Python
- Matlab
- Javascript