AMCS Seminar

Weiyu Xu
"Adversarial Fragility of Deep Learning Classifiers: An Information-Theoretic Explanation and An Information-Theory Inspired Defense"

We present a simple hypothesis about a compression property of artificial intelligence (AI) classifiers and present theoretical arguments to show that this hypothesis successfully accounts for the observed fragility of AI classifiers to small adversarial perturbations. We also propose a new method for detecting when small input perturbations cause classifier errors, and show theoretical guarantees for the performance of this detection method. We present experimental results which demonstrate this method. The ideas in this talk are motivated by a simple analogy between AI classifiers and the standard Shannon model of a communication system.

Event Date: 
April 12, 2019 - 3:30pm to 4:30pm
221 MLH
Calendar Category: 
Seminar Category: