Department
Computer Science and Cybersecurity
Document Type
Poster
Abstract
Field Programmable Gate Arrays (FPGAs) are widely used in defense systems, AI accelerators, and embedded devices because of their flexibility and reconfigurability. However, this flexibility also introduces critical security risks such as hardware Trojans and timing side channel vulnerabilities, which often go undetected by conventional verification tools. This study explores how artificial intelligence and machine learning can predict security vulnerabilities during the early design phase of FPGA development. By training AI models on datasets of both secure and compromised FPGA designs, the system learns to recognize potential weak points before bitstream generation. The goal is to integrate security directly into the design process, improving efficiency, reliability, and trust in FPGA based systems.
Publication Date
Fall 12-4-2025
Recommended Citation
Mohamed, Osob, "AI-Driven Prediction of Vulnerabilities in FPGA Designs" (2025). Student Scholarship. 16.
https://metroworks.metrostate.edu/student-scholarship/16
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Comments
Fall 2025:Student Research Conference