activity
20242026
collaborators

5 papers

cs.CV2026

Diffusion or Non-Diffusion Adversarial Defenses: Rethinking the Relation between Classifier and Adversarial Purifier

Yuan-Chih Chen, Chun-Shien Lu

Adversarial defense research continues to face challenges in combating against advanced adversarial attacks, yet with diffusion models increasingly favoring their defensive capabil…

cs.CV2025

FedSDA: Federated Stain Distribution Alignment for Non-IID Histopathological Image Classification

Cheng-Chang Tsai, Kai-Wen Cheng, Chun-Shien Lu

Federated learning (FL) has shown success in collaboratively training a model among decentralized data resources without directly sharing privacy-sensitive training data. Despite r…

cs.CR2025

MaXsive: High-Capacity and Robust Training-Free Generative Image Watermarking in Diffusion Models

Po-Yuan Mao, Cheng-Chang Tsai, Chun-Shien Lu

The great success of the diffusion model in image synthesis led to the release of gigantic commercial models, raising the issue of copyright protection and inappropriate content ge…

cs.LG2025

Test-time Adversarial Defense with Opposite Adversarial Path and High Attack Time Cost

Cheng-Han Yeh, Kuanchun Yu, Chun-Shien Lu

Deep learning models are known to be vulnerable to adversarial attacks by injecting sophisticated designed perturbations to input data. Training-time defenses still exhibit a signi…

cs.LG2024

Adversarial Robustness Overestimation and Instability in TRADES

Jonathan Weiping Li, Ren-Wei Liang, Cheng-Han Yeh +4

This paper examines the phenomenon of probabilistic robustness overestimation in TRADES, a prominent adversarial training method. Our study reveals that TRADES sometimes yields dis…