Secure and Efficient AI Hardware Implementation

Project Informtion

• Project Title: Collaborative Research: CISE-MSI:DP:CCF:SHF: MSI/HSI Research Capacity Building via Secure and Efficient Hardware Implementation of Cellular Computational Network

• Award Number: CNS-2131163

• Award Amount: $260,000 

• Project Period: 10/2021-09/2024

• Principal Investigator (PI): Dr. Taesic Kim (09/2023-09/2024)

• Graduate Students: Joaquin Massa, Lauren Silva, Alve Akash, Ameya Khot

• Undergraduate Students: Hugo Tavares-Vengas 

Project Overview

The main objective of this project, Collaborative Research: CISE-MSI: DP: CCF: SHF: MSI/HSI Research Capacity Building via Secure and Efficient Hardware Implementation of Cellular Computational Networks (CCN), is to initiate a partnership between Texas A&M University – Kingsville (TAMUK). This project propose to develop a secure and efficient hardware platform for implementing scalable and distributed Artificial Intelligence (AI) for Critical Networked Systems (CNSs), using Cellular Computational Network (CCN) learning framework. Dr. Kim will further investigate FPGA-based AI controller for smart inverter and decentralized intrusion detection using CCN as well as explore quantum machine learning.  

Publications 

1. J. Massa, K-T. Kim, T. Kim*, K. Venayagamoorthy, and J. Zeng, "Adversarial machine learning attack on machine learning-based controller for solar inverters,"  in Proc. 2024 IEEE Energy Conversion Congress and Exposition, 2024, accepted.

2. A. Khot, T. Kim*, A. Akash, C. H. Kim, and W. Moy, “Quantum-inspired machine learning framework using a physics-based Ising solver chip,” in Proc. 2024 International Conference on Industrial Cyber-Physical Systems, 2024, accepted.

3. A. Akash, B. Ahn, A. Jenkins, A. Khot, L. Silva, H. Tavares-Vengas, and T. Kim*, "Quantum convolutional neural network-based online malware file detection for smart grid devices," in Proc. 2023 IEEE Design Methodologies Conference, FL, USA, 2023, pp. 1-5.

4. 1. A. Akash, A. Khot, and T. Kim*, “Quantum annealing-based machine learning for battery health monitoring robust to adversarial attacks,” in Proc. 2023 IEEE Energy Conversion Congress and Exposition, Nashville, TN, USA, Oct.  29-Nov. 2023, pp. 6307-6311.