1 citations · 1 across the 4 of their papers we have counts for
3 papers · 1 filter
Revisiting the Provable-Auditable Privacy Gap of DP-SGD
Saloni Modi, Srivi Balaji, Yusong Zhu +2
Differential privacy (DP) has traditionally been used to provide theoretical upper bounds on an algorithm's stability to changing its training data. In modern private machine learn…
Rethinking Benchmarks for Differentially Private Image Classification
Sabrina Mokhtari, Sara Kodeiri, Shubhankar Mohapatra +2
We revisit benchmarks for differentially private image classification. We suggest a comprehensive set of benchmarks, allowing researchers to evaluate techniques for differentially…
Membership Inference Attacks Cannot Prove that a Model Was Trained On Your Data
Jie Zhang, Debeshee Das, Gautam Kamath +1
We consider the problem of a training data proof, where a data creator or owner wants to demonstrate to a third party that some machine learning model was trained on their data. Tr…