Adversarial Examples in Simpler Settings

In this thesis we explore adversarial examples for simple model families and simple data distributions, focusing in particular on linear and kernel classifiers. On the theoretical front we find evidence that natural accuracy and robust accuracy are more likely than not to be misaligned. We conclude from this that in order to learn a robust classifier, one should explicitly aim for it either via a good choice of model family or via optimizing explicitly for robust accuracy. On the empirical front we discover that kernel classifiers and neural networks are non-robust in similar ways. This suggests that a better understanding of kernel classifier robustness may help unravel some of the mysteries of adversarial examples.

Name thesis:degree_name

Master

Department dc:contributor.department

Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science

Grantor dc:publisher

Massachusetts Institute of Technology

Year dc:date.issued

2021

Author dc:creator

• Wang, Tony T.

Advisor dc:contributor.advisor

• Wornell, Gregory W.

Statement dc:rights

• In Copyright - Educational Use Permitted
• Copyright MIT

Licence dc:rights.uri

• http://rightsstatements.org/page/InC-EDU/1.0/

Handle dc:identifier.uri

https://hdl.handle.net/1721.1/139041

OAI identifier oai:identifier

oai:dspace.mit.edu:1721.1/139041