Probing the Transition to Dataset-Level Privacy in ML Models Using an Output-Specific and Data-Resolved Privacy Profile

no code implementations • 27 Jun 2023 • Tyler LeBlond, Joseph Munoz, Fred Lu, Maya Fuchs, Elliott Zaresky-Williams, Edward Raff, Brian Testa

Differential privacy (DP) is the prevailing technique for protecting user data in machine learning models.

A General Framework for Auditing Differentially Private Machine Learning

no code implementations • 16 Oct 2022 • Fred Lu, Joseph Munoz, Maya Fuchs, Tyler LeBlond, Elliott Zaresky-Williams, Edward Raff, Francis Ferraro, Brian Testa

We present a framework to statistically audit the privacy guarantee conferred by a differentially private machine learner in practice.

Eigenstate thermalization for observables that break Hamiltonian symmetries and its counterpart in interacting integrable systems

no code implementations • 3 Aug 2020 • Tyler LeBlond, Marcos Rigol

We study the off-diagonal matrix elements of observables that break the translational symmetry of a spin-chain Hamiltonian, and as such connect energy eigenstates from different total quasimomentum sectors.

Statistical Mechanics Quantum Gases Quantum Physics