activity
20242026
collaborators

5 papers

cs.CL2026

PEPPER: Perception-Guided Perturbation for Robust Backdoor Defense in Text-to-Image Diffusion Models

Oscar Chew, Po-Yi Lu, Jayden Lin +2

Recent studies show that text to image (T2I) diffusion models are vulnerable to backdoor attacks, where a trigger in the input prompt can steer generation toward harmful or uninten…

cs.LG2025

Soft Separation and Distillation: Toward Global Uniformity in Federated Unsupervised Learning

Hung-Chieh Fang, Hsuan-Tien Lin, Irwin King +1

Federated Unsupervised Learning (FUL) aims to learn expressive representations in federated and self-supervised settings. The quality of representations learned in FUL is usually d…

cs.LG2025

Tackling Dimensional Collapse toward Comprehensive Universal Domain Adaptation

Hung-Chieh Fang, Po-Yi Lu, Hsuan-Tien Lin

Universal Domain Adaptation (UniDA) addresses unsupervised domain adaptation where target classes may differ arbitrarily from source ones, except for a shared subset. A widely used…

cs.LG2024

MAX: Masked Autoencoder for X-ray Fluorescence in Geological Investigation

An-Sheng Lee, Yu-Wen Pao, Hsuan-Tien Lin +1

Pre-training foundation models has become the de-facto procedure for deep learning approaches, yet its application remains limited in the geological studies, where in needs of the…

cs.CV2024

Defending Text-to-image Diffusion Models: Surprising Efficacy of Textual Perturbations Against Backdoor Attacks

Oscar Chew, Po-Yi Lu, Jayden Lin +1

Text-to-image diffusion models have been widely adopted in real-world applications due to their ability to generate realistic images from textual descriptions. However, recent stud…