Privacy protection method for ADS-B air traffic control data based on convolutional neural network and symmetric...

Area of Science:

• Air Traffic Management
• Cybersecurity
• Data Privacy

Background:

• Automatic Dependent Surveillance-Broadcast (ADS-B) is crucial for modern air traffic management, providing real-time flight data.
• The open nature of ADS-B broadcasts poses significant privacy risks due to potential data interception and misuse.
• Effective mining and safeguarding of privacy information in ADS-B data present critical research challenges.

Purpose of the Study:

• To propose a novel privacy protection method for ADS-B air traffic control data.
• To address the challenges of data interception and misuse in ADS-B systems.
• To enhance the security and privacy of sensitive flight information.

Main Methods:

• Integration of deep learning techniques with symmetric encryption.
• Analysis of ADS-B air traffic monitoring architecture to identify and normalize privacy-related data.
• Development of a Convolutional Neural Network (CNN)-based classification model for sensitive information identification.

Main Results:

• The proposed method effectively scrambles original privacy information, preventing data theft or damage.
• Demonstrated efficiency in encryption times across various data volumes (10GB-40GB), with times ranging from 20.36ms to 50.36ms.
• Achieved robust privacy protection with shorter encryption times compared to existing methods.

Conclusions:

• The novel method offers an effective solution for privacy protection in ADS-B systems.
• The integration of deep learning and symmetric encryption provides efficient and robust data security.
• Future research should focus on advanced encryption and deep learning for enhanced ADS-B privacy protection.