51 citations · 153 across the 19 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.LG2026
Privacy Cost as Equity Input: A Group Fairness Criterion for Differentially Private Machine Learning
Rakshit Naidu
Differential privacy (DP) is increasingly deployed to limit membership inference risk in machine-learning systems. Prior work has shown that DP-SGD can widen accuracy disparities a…
cs.LG2026
Fair Finetuning Mitigates Distribution Inference Attacks
Rakshit Naidu
Machine learning models trained on sensitive data can inadvertently leak population-level information about their training distributions -- a threat known as distribution inference…