Inria 2018

Abstract

Deep neural networks present strong vulnerabilities against adversarial examples, model theft and privacy of datasets. On the other side, software verification is a well-researched field, with about 40 years of cumulated expertise, tools and techniques. We aim to present two techniques widely used in software verification; Abstract Interpretation and Satisfactory Modulo Theories solvers, and how we can leverage them to obtain provably more robust deep neural networks.

Date
Dec 13, 2018 2:00 PM

Deep neural networks present strong vulnerabilities against adversarial examples, model theft and privacy of datasets. On the other side, software verification is a well-researched field, with about 40 years of cumulated expertise, tools and techniques. We aim to present two techniques widely used in software verification; Abstract Interpretation and Satisfactory Modulo Theories solvers, and how we can leverage them to obtain provably more robust deep neural networks.

A video recording is available here.

Researcher on Trustworthy Artificial Intelligence