Farhad Farokhi

Gradient Sparsification Can Improve Performance of Differentially-Private Convex Machine Learning

2020 · arXiv (Cornell University)

We use gradient sparsification to reduce the adverse effect of differential privacy noise on performance of private machine learning models. To this aim, we employ compressed sensing and additive Laplace noise to evaluate differentially-private gradients. …

Barycentric and Pairwise Renyi Quantum Leakage

2024 · arXiv (Cornell University)

Barycentric and pairwise quantum Renyi leakages are proposed as two measures of information leakage for privacy and security analysis in quantum computing and communication systems. These quantities both require minimal assumptions on the eavesdropper, i.e., …