Artificial intelligence driven approach for securing backup data and enhancing cyber resilience in sustainable smart...

Area of Science:

• Computer Science
• Cybersecurity
• Artificial Intelligence

Background:

• Smart cities face significant cyber threats due to increased connectivity.
• Conventional cyber resilience frameworks often neglect backup data integrity verification.
• This gap compromises data restoration and overall system resilience.

Purpose of the Study:

• To implement an AI-powered approach for backup data integrity verification.
• To enhance cyber resilience (CR) in smart infrastructure.
• To address limitations in conventional resilience frameworks regarding data restoration.

Main Methods:

• Utilized Murmur Polytopes Hash (MPH) for backup data integrity verification.
• Developed an AI-based ransomware attack detection module for smart infrastructure.
• Integrated node initialization, clustering, data security, and storage (Cloud and IPFS).
• Employed Merkle trees for hash code generation and updates.

Main Results:

• Achieved high security levels and accuracy rates of 98.45% (security) and 98.65% (accuracy).
• Demonstrated improved resilience through effective backup data integrity checks.
• Successfully verified backup data integrity using MPH before restoration.

Conclusions:

• The proposed AI-powered MPH approach significantly enhances cyber resilience in smart cities.
• Ensuring backup data integrity is critical for effective data restoration and security.
• The system offers a robust solution for protecting smart infrastructure against cyber threats.