2 papers
cs.LG2026
Classification-Head Bias in Class-Level Machine Unlearning: Diagnosis, Mitigation, and Evaluation
Weidong Zheng, Kongyang Chen, Yuanwei Guo +1
Class-level machine unlearning aims to remove the influence of specified classes while preserving model utility on retained classes. Existing methods are commonly evaluated by reta…
cs.CR2026
Label Leakage Attacks in Machine Unlearning: A Parameter and Inversion-Based Approach
Weidong Zheng, Kongyang Chen, Yao Huang +2
With the widespread application of artificial intelligence technologies in face recognition and other fields, data privacy security issues have received extensive attention, especi…