ORCID Number
0009-0006-7969-3277
Date of Award
Spring 5-4-2026
Access Type
Dissertation - Open Access
Degree Name
Doctor of Philosophy in Electrical Engineering & Computer Science
Department
Electrical, Computer, Software, and Systems Engineering
Committee Chair
Omar Ochoa
Committee Chair Email
ochoao@erau.edu
First Committee Member
Laxima Niure Kandel
First Committee Member Email
niurekal@erau.edu
Second Committee Member
Salamah Salamah
Second Committee Member Email
isalamah@utep.edu
Third Committee Member
Richard S. Stansbury
Third Committee Member Email
stansbur@erau.edu
Fourth Committee Member
Alex Vargas Acosta
Fourth Committee Member Email
vargasar@erau.edu
College Dean
James W. Gregory
Abstract
Cybersecurity has become a global concern as cyber-attacks have become more common, and the cost of the damage caused by them continues to increase. There are several approaches to improve the cyber security of systems such as Digital Signatures, hashing, watermarking, and encryption among others. Digital Signatures are a cryptographic technique used to verify the authenticity and integrity of digital messages or documents. Digital Signatures use a combination of hashing and public-private key encryption to verify the authenticity and integrity of videos, just as they are used for documents and messages. As a result of using a combination of other methods, Digital Signatures inherit the weaknesses from the hashing algorithm used, which include collisions, preimage resistance, or poor performance. specializes in enabling systems to learn from data and improve performance over time without being explicitly programmed. Machine Learning algorithms leverage statistical techniques to identify patterns and make predictions or decisions based on historical data. Unlike traditional software that follows a fixed set of rules, Machine Learning models adapt and refine their predictions as they are exposed to more data. The goal of this research is to show that Machine Learning can be used to generate Digital Signatures and be as successful as current methods for Digital Signature generation and verification to make more resilient and robust methods. The hashing section of the Digital Signature would be replaced by a Machine Learning model which will hash the message sent. The performance of the new Digital Signature process will be compared to regular Digital Signature methods using time to sign, time to verify, and resource usage (RAM and memory). We posit that Machine Learning generated Digital Signatures can have comparable performance to traditionally generated Digital Signatures while potentially increasing security.
Scholarly Commons Citation
Ortiz Couder, Juan, "Security Assessment of a Machine Learning Approach to Generate and Validate Digital Signatures" (2026). Doctoral Dissertations and Master's Theses. 986.
https://commons.erau.edu/edt/986
Included in
Artificial Intelligence and Robotics Commons, Cybersecurity Commons, Information Security Commons
