Cyber Vulnerabilities and Risks of AI Technologies in Space Applications
Résumé
Artificial Intelligence (AI) is becoming a key technology for space applications. Recently, AI has come into extensive use in spacecraft operations, for example to support highly efficient operations of satellite constellations. This ranges in applications from relative positioning, Earth Observation, autonomous navigation, and end-of-life management, among others. While the importance of AI is rising for new space assets, AI is vulnerable to cyber threats, and AI cyber security is becoming an important aspect of space safety and operational security. This work aims to identify the vulnerabilities that AI systems may introduce to space assets and to analyse the potential operational threats and effective technological and regulatory mitigation measures. Towards this goal, the paper first examines and differentiates between vulnerabilities in legacy space systems, and those that are particularly related to AI technologies. The analysis covers the definition of AI technology as well as a detailed discussion about its current use in space related applications. Secondly, a comparison between prevailing cyber-attacks in space and cyber-attacks targeting AI technologies is made. Based on this assessment, the paper recommends prevention and mitigation measures that are contingent on cyber resilience of space operations focusing on AI-based space applications.
Origine : Fichiers produits par l'(les) auteur(s)