Locally optimal detection and randomization defenses against universal adversarial perturbations

This thesis investigates a detection-based approach to safeguard a machine-learning based classifier from adversarial perturbations of its input. In particular, we consider input agnostic universal adversarial perturbations which are selected to force the input to a desired target class. The detector is designed by application of fundamental concepts of statistical decision theory, including locally optimal testing. Since locally optimal detectors depend on the input distribution, which is unknown in real-world datasets, a tractable surrogate input distribution is used instead. The thesis also defines several metrics for joint classification and detection, and evaluates them on several image datasets and popular image classifiers. We demonstrate through the experimental results that our detection-based approach is successful and outperforms the prior state of the art. We also show that detector-aware universal adversarial perturbations can be constructed in a way that evades our detector and achieves high target success rate on the classifier. To mitigate this problem, we propose and evaluate several relevant randomization schemes. Among the proposed methods, we observe that randomized smoothing offers better defense against the stronger detector-aware attacks.

Name thesis:degree_name

Ph.D.

Level thesis:degree_level

Dissertation

Discipline thesis:degree_discipline

Electrical & Computer Engr

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2022

Author dc:creator

• Goel, Amish

Contributors dc:contributor

• Moulin, Pierre
• Schwing, Alexander
• Li, Bo
• Raginsky, Maxim
• Veeravalli, Venugopal V.

• universal adversarial perturbations
• deep learning
• hypothesis testing
• locally optimal test
• generalized likelihood ratio test

Statement dc:rights

• Copyright 2022 Amish Goel

Language dc:language

en, eng

Handle dc:identifier

https://hdl.handle.net/2142/117625

OAI record oai:identifier

https://www.ideals.illinois.edu/oai-pmh?verb=GetRecord&metadataPrefix=etdms&identifier=oai%3Awww.ideals.illinois.edu%3A2142%2F117625