DYNAMIC DEFENSES AND THE TRANSFERABILITY OF ADVERSARIAL EXAMPLES

ECU Author/Contributor (non-ECU co-authors, if there are any, appear on document)

Sam Thomas (Creator)

Institution

East Carolina University (ECU )

Web Site: http://www.ecu.edu/lib/

Abstract: Adversarial machine learning has been an important area of study for the securing of machine learning systems. However , for every defense that is made to protect these artificial learners , a more sophisticated attack emerges to defeat it. This has created an arms race , with the problem of adversarial attacks never being fully mitigated. This thesis examines the field of adversarial machine learning; specifically , the property of transferability , and the use of dynamic defenses as a solution to attacks which leverage it. We show that this is an emerging field of research , which may be the solution to one of the most intractable problems in adversarial machine learning. We go on to implement a minimal experiment , demonstrating that research within this area is easily accessible. Finally , we address some of the hurdles to overcome in order to unify the disparate aspects of current related research.

Additional Information

Publication

Thesis

Language: English

Date: 2019

Keywords

adversarial machine learning, transferability

Subjects

Email this document to