Подписаться
Yu-Lin Tsai
Yu-Lin Tsai
National Yang Ming Chiao Tung University
Подтвержден адрес электронной почты в домене nycu.edu.tw
Название
Процитировано
Процитировано
Год
Ring-A-Bell! How Reliable are Concept Removal Methods for Diffusion Models?
YL Tsai, CY Hsu, C Xie, CH Lin, JY Chen, B Li, PY Chen, CM Yu, ...
arXiv preprint arXiv:2310.10012, 2023
332023
Formalizing generalization and adversarial robustness of neural networks to weight perturbations
YL Tsai, CY Hsu, CM Yu, PY Chen
Advances in Neural Information Processing Systems 34, 19692-19704, 2021
252021
Certified robustness of quantum classifiers against adversarial examples through quantum noise
JC Huang, YL Tsai, CHH Yang, CF Su, CM Yu, PY Chen, SY Kuo
ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023
182023
Formalizing generalization and robustness of neural networks to weight perturbations
YL Tsai, CY Hsu, CM Yu, PY Chen
arXiv preprint arXiv:2103.02200, 2021
142021
Exploring the benefits of visual prompting in differential privacy
Y Li, YL Tsai, CM Yu, PY Chen, X Ren
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2023
112023
Non-singular adversarial robustness of neural networks
YL Tsai, CY Hsu, CM Yu, PY Chen
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021
72021
Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models
CY Hsu, YL Tsai, CH Lin, PY Chen, CM Yu, CY Huang
arXiv preprint arXiv:2405.16833, 2024
42024
Differentially Private Fine-Tuning of Diffusion Models
YL Tsai, Y Li, Z Chen, PY Chen, CM Yu, X Ren, F Buet-Golfouse
arXiv preprint arXiv:2406.01355, 2024
2024
Toward Non-Singular Robustness of Neural Networks
YL Tsai, CY Hsu, CM Yu, PY Chen
International Conference on Learning Representations, 2021
2021
В данный момент система не может выполнить эту операцию. Повторите попытку позднее.
Статьи 1–9