Robustness and Vulnerability Measures of Deep Learning Methods for Cyber Defense
Abstract
Navy networks and infrastructures are under frequent cyberattack. One developing area of application of Artificial Intelligence (AI) and Machine Learning (ML) is cybersecurity. However, some weakness of machine learning, such as the lack of interpretability and the susceptibility to adversarial data, are important issues that must be studied for reliable and safe applications of AI tools. The robustness of deep learning (DL) techniques used in computer vision and language processing have been extensively studied. However, less is currently known about the vulnerabilities and robustness of DL methods suitable in cybersecurity applications. The goal of this research is to investigate mathematical concepts and quantitative measures of robustness and vulnerability to adversarial data for cybersecurity DL and to create computational algorithms capable of quantitatively evaluating the robustness and vulnerability of DL tools. The tasks of the project include literature review, an innovative study of mathematical concepts, the development of computational algorithms, the validation of the concepts and algorithms through examples. The deliverables of the project include technical reports, student thesis, and technical papers for publication. This work will enhance understanding of vulnerabilities of deep learning systems that could be incorporated in future DoN networks, and provide the US Navy with computational tools capable of measuring the robustness of the AI enabled systems.
Description
NPS NRP Technical Report
Rights
This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.NPS Report Number
PS-MA-23-001Related items
Showing items related by title, author, creator and subject.
-
Robustness and Vulnerability Measures of Deep Learning Methods for Cyber Defense
Martinsen, Thor; Kang, Wei (Monterey, California: Naval Postgraduate School, 2022);Navy networks and infrastructures are under frequent cyberattack. One developing area of application of Artificial Intelligence (AI) and Machine Learning (ML) is cybersecurity. However, some weakness of machine learning, ... -
Applying Cause-Effect Mapping to Assess Cybersecurity Vulnerabilities in Model-Centric Acquisition Program Environment
Reid, Jack; Rhodes, Donna (Monterey, California. Naval Postgraduate School, 2018-04-30); SYM-AM-18-175Digital engineering approaches are increasingly used in acquisition of systems, changing the current paradigm from documentation-centric to model-centric. Not only are these systems highly vulnerable to cyber threats, so ... -
Applying Cause-Effect Mapping to Assess Cybersecurity Vulnerabilities in Model-Centric Acquisition Program Environments
Reid, Jack; Rhodes, Donna H. (Monterey, California. Naval Postgraduate School, 2018-04-30); SYM-AM-18-090Digital engineering approaches are increasingly used in acquisition of systems, changing the current paradigm from documentation-centric to model-centric. Not only are these systems highly vulnerable to cyber threats, so ...