Cyber-Attack Resilient Distributed and Explainable AI with Zero Trust Architecture

Researchers aim to design stakeholder-centric, secure data-sharing and analytics systems focused on algorithms and frameworks that integrate federated learning (FL) and artificial intelligence (AI) to address big data collaborative supply chains’  security challenges.

Funded by CCI’s Coastal Virginia Node and Southwest Virginia Node

Project Investigators

• Primary Investigator (PI): Rafael Diaz, Old Dominion University School of Cybersecurity
• Co-PI: Bikash Chandra Singh, Old Dominion University School of Cybersecurity
• Co-PI: Zeb Bowden, Virginia Tech Transportation Institute

Rationale

Supply chains involve multiple stakeholders bound by data-privacy and confidentiality requirements, creating a complex security environment for such industries as supply chain management, health care, and finance. 

Organizations want and need to unlock the full potential of big data analytics while maintaining compliance with data protection regulations, fostering greater trust and cooperation among stakeholders.

Projected Outcomes

Stakeholders will be able to train AI models collaboratively while maintaining the confidentiality of their sensitive information, ensuring that global model updates are validated through a zero-trust architecture. This will provide an additional layer of security. 

The zero-trust model will also enforce strict validation protocols, ensuring continuous protection for local models and mitigating the risk of unauthorized access or breaches. This will enable secure data analysis without the need for raw data sharing.