1 citations · 1 across the 2 of their papers we have counts for
2 papers
cs.CR2026
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…
cs.LG2024★ 1 cited
The Power of Bias: Optimizing Client Selection in Federated Learning with Heterogeneous Differential Privacy
Jiating Ma, Yipeng Zhou, Qi Li +3
To preserve the data privacy, the federated learning (FL) paradigm emerges in which clients only expose model gradients rather than original data for conducting model training. To…