Robust and Trustworthy Deep Learning: Attacks, Defenses and Designs

Author

Bingyin ZhaoFollow

Date of Award

5-2024

Document Type

Dissertation

Degree Name

Doctor of Philosophy (PhD)

Department

Electrical and Computer Engineering (Holcomb Dept. of)

Committee Chair/Advisor

Yingjie Lao

Committee Member

Jon Calhoun

Committee Member

Shuhong Gao

Committee Member

Yongkai Wu

Abstract

Deep neural networks (DNNs) have achieved unprecedented success in many fields. However, robustness and trustworthiness have become emerging concerns since DNNs are vulnerable to various attacks and susceptible to data distributional shifts. Attacks such as data poisoning and out-of-distribution scenarios such as natural corruption significantly undermine the performance and robustness of DNNs in model training and inference and impose uncertainty and insecurity on the deployment in real-world applications. Thus, it is crucial to investigate threats and challenges against deep neural networks, develop corresponding countermeasures, and dig into design tactics to secure their safety and reliability. The works investigated in this dissertation constitute our pioneering efforts in robust and trustworthy deep learning from perspectives of attacks, defenses and designs.

Recommended Citation

Zhao, Bingyin, "Robust and Trustworthy Deep Learning: Attacks, Defenses and Designs" (2024). All Dissertations. 3637.
https://tigerprints.clemson.edu/all_dissertations/3637

Author ORCID Identifier

https://orcid.org/0000-0003-0372-8198