1 citations · 1 across the 4 of their papers we have counts for
4 papers
CoLA: A Choice Leakage Attack Framework to Expose Privacy Risks in Subset Training
Qi Li, Cheng-Long Wang, Yinzhi Cao +1
Training models on a carefully chosen portion of data rather than the full dataset is now a standard preprocess for modern ML. From vision coreset selection to large-scale filterin…
Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Unlearning Completeness
Cheng-Long Wang, Qi Li, Zihang Xiang +2
Growing concerns over data privacy and security highlight the importance of machine unlearning--removing specific data influences from trained models without full retraining. Techn…
Data Lineage Inference: Uncovering Privacy Vulnerabilities of Dataset Pruning
Qi Li, Cheng-Long Wang, Yinzhi Cao +1
In this work, we systematically explore the data privacy issues of dataset pruning in machine learning systems. Our findings reveal, for the first time, that even if data in the re…
Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Approximate Unlearning Completeness
Cheng-Long Wang, Qi Li, Zihang Xiang +2
By adopting a more flexible definition of unlearning and adjusting the model distribution to simulate training without the targeted data, approximate machine unlearning provides a…