Bounding the Excess Risk for Linear Models Trained on Marginal-Preserving, Differentially-Private, Synthetic Data

no code implementations • 6 Feb 2024 • Yvonne Zhou, Mingyu Liang, Ivan Brugere, Dana Dachman-Soled, Danial Dervovic, Antigoni Polychroniadou, Min Wu

The growing use of machine learning (ML) has raised concerns that an ML model may reveal private information about an individual who has contributed to the training dataset.

Mystique: Enabling Accurate and Scalable Generation of Production AI Benchmarks

no code implementations • 16 Dec 2022 • Mingyu Liang, Wenyin Fu, Louis Feng, Zhongyi Lin, Pavani Panakanti, Shengbao Zheng, Srinivas Sridharan, Christina Delimitrou

We evaluate our methodology on several production AI models, and show that benchmarks generated with Mystique closely resemble original AI models, both in execution time and system-level metrics.