3 papers
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.CV2024
Defending Against Repetitive Backdoor Attacks on Semi-supervised Learning through Lens of Rate-Distortion-Perception Trade-off
Cheng-Yi Lee, Ching-Chia Kao, Cheng-Han Yeh +3
Semi-supervised learning (SSL) has achieved remarkable performance with a small fraction of labeled data by leveraging vast amounts of unlabeled data from the Internet. However, th…
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…