Weidong Zheng
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
Crypto×2ML×1
Frequent co-authors
Research Timeline
2026
Label Leakage Attacks in Machine Unlearning: A Parameter and Inversion-Based Approach
This paper analyzes and proposes four novel attack methods—based on model parameters and model inversion—to demonstrate that existing machine unlearning techniques can inadvertently leak the categories of the forgotten data.
Classification-Head Bias in Class-Level Machine Unlearning: Diagnosis, Mitigation, and Evaluation
This paper diagnoses a bias-dominated shortcut in class-level machine unlearning, where forgetting is achieved by suppressing classification head biases, and proposes bias-aware mechanisms to mitigate this issue.
Highlighted terms show continued research focus across papers
Papers
cs.LGcs.CRRecentMay 9, 2026
Classification-Head Bias in Class-Level Machine Unlearning: Diagnosis, Mitigation, and Evaluation
This paper diagnoses a bias-dominated shortcut in class-level machine unlearning, where forgetting is achieved by suppressing classification head biases, and proposes bias-aware mechanisms to mitigate…
View →
cs.CRRecentApr 8, 2026