Hardware/Algorithm Codesign for Adversarially Robust Deep Learning

Mojan Javaheripi, Mohammad Samragh, Bita Darvish Rouhani, Tara Javidi, Farinaz Koushanfar

Abstract: italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Editor’s note:</i> This article describes DeepFense, a framework to make deep learning models automatically and efficiently realizable on constrained devices. — <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Rosario Cammarota, Intel Labs</i> — <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Francesco Regazzoni, University of Amsterdam and Università della Svizzera Italiana</i>