Local Competition and Stochasticity for Adversarial Robustness in Deep Learning

Konstantinos P. Panousis, Antonios Alexos, Sergios Theodoridis, Sotirios Chatzis

Research output: Contribution to journalConference article in JournalResearchpeer-review

3 Citations (Scopus)
11 Downloads (Pure)

Abstract

This work addresses adversarial robustness in deep learning by considering deep networks with stochastic local winner-takes-all (LWTA) activations. This type of network units result in sparse representations from each model
layer, as the units are organized in blocks where only one unit generates a non-zero output. The main operating principle of the introduced units lies on stochastic arguments, as the network performs posterior sampling over
competing units to select the winner. We combine these LWTA arguments with tools from the field of Bayesian non-parametrics, specifically the stick-breaking construction of the Indian Buffet Process, to allow for inferring the sub-part of each layer that is essential for modeling the data at hand. Then, inference is
performed by means of stochastic variational Bayes. We perform a thorough experimental evaluation of our model using benchmark datasets. As we show, our method achieves high robustness to adversarial perturbations,
with state-of-the-art performance in powerful adversarial attack schemes.
Original languageEnglish
Book seriesThe Proceedings of Machine Learning Research
Volume130
Number of pages11
ISSN2640-3498
Publication statusPublished - 2021
Event24th International Conference on Artificial Intelligence and Statistics (AISTATS) 2021 - San Diego, United States
Duration: 13 Apr 202115 Apr 2021

Conference

Conference24th International Conference on Artificial Intelligence and Statistics (AISTATS) 2021
Country/TerritoryUnited States
CitySan Diego
Period13/04/202115/04/2021

Fingerprint

Dive into the research topics of 'Local Competition and Stochasticity for Adversarial Robustness in Deep Learning'. Together they form a unique fingerprint.

Cite this