3 papers
cs.LG2025
RUB: Evaluating Residual Knowledge in Unlearned Models
Hao Xuan, Xingyu Li
Machine Unlearning (MUL) has emerged as a key mechanism for privacy protection and content regulation, yet current techniques often fail to guarantee the complete removal of sensit…
cs.LG2025
Exploring the Impact of Temperature Scaling in Softmax for Classification and Adversarial Robustness
Hao Xuan, Bokai Yang, Xingyu Li
The softmax function is a fundamental component in deep learning. This study delves into the often-overlooked parameter within the softmax function, known as "temperature," providi…
cs.LG2023
Advancing Adversarial Robustness Through Adversarial Logit Update
Hao Xuan, Peican Zhu, Xingyu Li
Deep Neural Networks are susceptible to adversarial perturbations. Adversarial training and adversarial purification are among the most widely recognized defense strategies. Althou…