Robust Machine Learning on the Edge (Feb 27)

Date: Feb 27, 11:15 – 12:15 pm

Abstract:

Adversarial robustness, i.e., the ability of a machine learning (ML) algorithm to maintain its predictive power under input perturbations, is an important property for many safety-critical applications. It is even more important in edge deployments of ML algorithms, where inference is performed in a resource-constrained, open environment. We investigate the use of the Hilbert-Schmidt independence criterion (HSIC) as a regularizer to train an adversarially robust deep neural network. We prove that the resulting regularizer reduces the sensitivity of the classifier to adversarial perturbations and show that it can enhance the quality of latent representations through compression. We also show that, when combined with knowledge distillation, our regularizer can be used to prune a previously trained robust neural network while maintaining adversarial robustness, again without any further generation of adversarial examples. This yields significant computational dividends, compressing large networks 4-7 times faster than state-of-the-art adversarial pruning methods.

Biographical Sketch

Stratis Ioannidis is Professor in the Electrical and Computer Engineering Department of Northeastern University, in Boston, MA, where he also holds a courtesy appointment with the Khoury College of Computer Sciences. He received his B.Sc. (2002) in Electrical and Computer Engineering from the National Technical University of Athens, Greece, and his M.Sc. (2004) and Ph.D. (2009) in Computer Science from the University of Toronto, Canada. Prior to joining Northeastern, he was a research scientist at the Technicolor research centers in Paris, France, and Palo Alto, CA, as well as at Yahoo Labs in Sunnyvale, CA. He is the recipient of an NSF CAREER Award, a Google Faculty Research Award, a Facebook Research Award, a Søren Buus Outstanding Research Award, a Martin W. Essigmann Outstanding Teaching Award, and several best paper awards. His research interests span machine learning, distributed systems, networking, optimization, and privacy.

Location: LOV 307 and ZOOM