TOWARDS A LEARNING-BASED DYNAMIC DATA DRIVEN DETECTION FRAMEWORK FOR UNFORESEEN CYBER ATTACKS

Abstract

This project addresses the aforementioned challenges. The significance of this project is to advance the foundation for designing an efficient and cost-effective learning-based detection framework in CPS to ensure system protection and infrastructure economics, as well as to advance the scientific understanding of the impacts of unforeseen cyber-attacks in CPS. The novelty and unique contributions of this project include techniques to develop a generic unsupervised deep learning-based detection framework for unforeseen cyber-attacks in CPS, design an edge-assisted distributed detection framework to explore distributed attacks, and generic co-simulation and hardware-in-the-loop emulation platforms for CPS research and education. The outcome of this project will provide not only the scientific foundation for designing cybersecurity frameworks in CPS, but also the scientific foundation for understanding and explaining attack and defense behaviors in CPS.

Document Details

Document Type
DoD Grant Award
Publication Date
Aug 12, 2021
Source ID
FA95502010418

Entities

People

  • Wei Yu

Organizations

  • Air Force Office of Scientific Research
  • Towson University
  • United States Air Force

Tags

Fields of Study

  • Computer science

Readers

  • Cybersecurity.
  • Distributed Systems and Data Platform Development

Technology Areas

  • AI & ML
  • Cyber