Securing Data in Vehicles: Privacy-Preserving Frameworks for Dynamic CAV Environments

Area of Science:

• Intelligent Transportation Systems
• Cybersecurity
• Data Privacy

Background:

• Connected and Autonomous Vehicles (CAVs) integrate advanced automation and connectivity.
• Vehicle-to-Everything (V2X) communication is crucial for CAVs but raises privacy concerns.
• Dynamic CAV environments present unique challenges for privacy preservation.

Purpose of the Study:

• Investigate evolving data privacy risks in CAV systems.
• Critically review existing privacy-preserving approaches and their limitations.
• Explore enabling technologies for privacy preservation in CAVs.

Main Methods:

• Literature review of privacy-preserving mechanisms.
• Analysis of Federated Learning, permissioned blockchain, and Software-Defined Networking (SDN).
• Assessment of technological limitations in dynamic vehicular contexts.

Main Results:

• Existing privacy models struggle with the dynamic nature of CAVs.
• Federated Learning, blockchain, and SDN show promise for privacy preservation.
• Specific limitations of current approaches in high-mobility environments were identified.

Conclusions:

• Targeted recommendations for optimizing privacy frameworks in CAVs.
• Enhancing privacy resilience is key for next-generation intelligent transportation.
• Need for scalable and robust privacy solutions for widespread CAV adoption.