Enhancing reliability and security in cloud-based telesurgery systems leveraging swarm-evoked distributed federated...

Area of Science:

• Robotics
• Cybersecurity
• Artificial Intelligence

Background:

• Robotic surgery advancements integrate AI, IoT, and 5G/6G, improving precision.
• Telesurgery and tele-mentoring face cybersecurity threats, impacting patient safety and system reliability.

Purpose of the Study:

• To propose a distributed federated learning framework to enhance cybersecurity in robotic surgery.
• To integrate Optimized Gated Transformer Networks (OGTN) with chaotic encryption for robust cyberattack mitigation.

Main Methods:

• Developed a federated learning framework using TensorFlow Federated Learning Libraries (FLL).
• Integrated OGTN with layered chaotic encryption schemes.
• Evaluated performance on the UNSW-NB15 dataset using precision, accuracy, F1-score, recall, and security strength.

Main Results:

• The proposed framework demonstrated superior diagnostic accuracy and cybersecurity resilience compared to conventional models.
• Security assessments aligned with NIST recommendations validated the framework's robustness.
• The system effectively preserved data privacy and integrity against cyber threats.

Conclusions:

• The developed framework is a viable solution for enhancing security in teleoperated healthcare systems.
• It offers improved operational efficiency and cybersecurity resilience for robotic surgery applications.
• Federated learning with OGTN and chaotic encryption shows promise for secure telesurgery.