TinyML-Driven Cybersecurity for Autonomous Spacecraft: Latency-Accuracy Analysis for SPARTA RF and Cyber Threat Detection
A new research paper analyzes the performance of TinyML models for cybersecurity threats on autonomous spacecraft. The study focuses on the latency-accuracy trade-offs of classical machine learning models like Random Forest and Logistic Regression when detecting various cyber-RF attacks. Results indicate that Logistic Regression offers microsecond-level inference with a minimal accuracy decrease, making it a suitable baseline for onboard spacecraft autonomy. AI
IMPACT This research could lead to more efficient and secure onboard AI systems for autonomous spacecraft.