51 citations · 153 across the 19 of their papers we have counts for
7 papers · 1 filter
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…
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…
Personalized Differential Privacy for Ridge Regression
Krishna Acharya, Franziska Boenisch, Rakshit Naidu +1
The increased application of machine learning (ML) in sensitive domains requires protecting the training data through privacy frameworks, such as differential privacy (DP). DP requ…
Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Tools
Emily Black, Rakshit Naidu, Rayid Ghani +3
While algorithmic fairness is a thriving area of research, in practice, mitigating issues of bias often gets reduced to enforcing an arbitrarily chosen fairness metric, either by e…
Pruning has a disparate impact on model accuracy
Cuong Tran, Ferdinando Fioretto, Jung-Eun Kim +1
Network pruning is a widely-used compression technique that is able to significantly scale down overparameterized models with minimal loss of accuracy. This paper shows that prunin…
Efficient Hyperparameter Optimization for Differentially Private Deep Learning
Aman Priyanshu, Rakshit Naidu, Fatemehsadat Mireshghallah +1
Tuning the hyperparameters in the differentially private stochastic gradient descent (DPSGD) is a fundamental challenge. Unlike the typical SGD, private datasets cannot be used man…
DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy?
Archit Uniyal, Rakshit Naidu, Sasikanth Kotti +4
Recent advances in differentially private deep learning have demonstrated that application of differential privacy, specifically the DP-SGD algorithm, has a disparate impact on dif…