Analysis of Dominant Classes in Universal Adversarial Perturbations

The reasons why Deep Neural Networks are susceptible to being fooled by adversarial examples remains an open discussion. Indeed, many differ- ent strategies can be employed to efficiently generate adversarial attacks, some of them relying on different theoretical justifications. Among these strategi...

Full description

Bibliographic Details
Authors: Vadillo, J., Santana, R., Lozano, J.A.
Format: article
Status:Published version
Publication Date:2022
Country:España
Institution:Basque Center for Applied Mathematics (BCAM)
Repository:BIRD. BCAM's Institutional Repository Data
OAI Identifier:oai:bird.bcamath.org:20.500.11824/1460
Online Access:http://hdl.handle.net/20.500.11824/1460
Access Level:Open access
Keyword:Adversarial examples
Universal Adversarial Perturbations
Deep Neural Networks
Robust Speech Classification
Description
Summary:The reasons why Deep Neural Networks are susceptible to being fooled by adversarial examples remains an open discussion. Indeed, many differ- ent strategies can be employed to efficiently generate adversarial attacks, some of them relying on different theoretical justifications. Among these strategies, universal (input-agnostic) perturbations are of particular inter- est, due to their capability to fool a network independently of the input in which the perturbation is applied. In this work, we investigate an in- triguing phenomenon of universal perturbations, which has been reported previously in the literature, yet without a proven justification: universal perturbations change the predicted classes for most inputs into one par- ticular (dominant) class, even if this behavior is not specified during the creation of the perturbation. In order to justify the cause of this phe- nomenon, we propose a number of hypotheses and experimentally test them using a speech command classification problem in the audio domain as a testbed. Our analyses reveal interesting properties of universal per- turbations, suggest new methods to generate such attacks and provide an explanation of dominant classes, under both a geometric and a data- feature perspective.