5 papers
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…
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…
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…
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…
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…