Skip to content
conftrace_
2025 ICML ICML 2025

PTTA: Purifying Malicious Samples for Test-Time Model Adaptation

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Jing Ma, Hanlin Li, Xiang Xiang

Topics

Artificial Intelligence > Core AI > AI Safety Machine Learning > Application Areas > Domain Adaptation Deep Learning > Learning Types > Transfer Learning

Keywords

test-time adaptation purification mixup benign samples malicious samples saliency indicator
Download PDF