KP Labs and European Space Agency Launch PINEBERRY Project to Revolutionize AI in Space Operations

PINEBERRY, which stands for Explainable, Robust, and Secure AI for Demystifying Space Mission Operations, focuses on two foundational pillars: Explainable AI (XAI) and Secure AI (SAI). These elements are essential for addressing the challenges posed by the increasing reliance on AI in space missions. XAI ensures that AI systems remain transparent, providing human operators with clear insights into the decision-making processes of autonomous systems. SAI, on the other hand, safeguards these systems against threats that could compromise mission success, such as data corruption or adversarial attacks. The project also emphasizes that XAI is designed to explain AI models to users, researchers, and developers, helping them understand how these systems work and increasing trust in their reliability. Similarly, SAI protects systems from vulnerabilities like data poisoning, prompt injection attacks, and overreliance.

Why Security and Explainability Matter?
Space missions depend on reliable data transmission from spacecraft to Earth. Any instance of data corruption, whether intentional or accidental, can jeopardize mission-critical operations, ranging from spacecraft navigation to scientific experiments. At PINEBERRY, advanced techniques such as data sanitization, robust training strategies (e.g., ensembling), and continuous model monitoring are being implemented to address these risks.

Additionally, ESA controllers require a deep understanding of AI systems' decision-making processes, especially in high-stakes scenarios where human oversight is limited. The XAI methods developed within PINEBERRY demystify the "black-box" nature of AI models, providing transparency across diverse data types, including telemetry, natural language reports, and computer vision data.

Practical Applications and a Look to the Future
The project’s innovations are demonstrated through realistic mission scenarios, prepared exactly for PINEBERRY, which showcase the implementation of advanced security and explainability techniques. Additionally, five proof-of-concept applications have been developed to tackle challenges in computer vision, time series data, and natural language processing. These solutions not only highlight opportunities for AI developers but also address vulnerabilities specific to ESA’s mission needs.

Professor Przemysław Biecek from the MI2.AI team of the Warsaw University of Technology also highlights the project’s significance: 

The project will further engage the community through a series of "Secure Your AI" data science challenges in 2025, including tasks like "Fake or Real" and "Data Heist." Participants will explore real-world scenarios by hacking and securing AI models for satellite telemetry analysis. The initiative will culminate in a grand Hackathon Day, fostering innovation and collaboration within the space and AI communities.

Collaborative Efforts Driving Innovation
PINEBERRY also exemplifies the power of collaboration, so crucial in the space industry. While ESA oversees the project’s alignment with European space standards, KP Labs leads the technical development of secure and explainable AI frameworks. Warsaw University of Technology contributes cutting-edge research on AI security and explainability, and ESA’s ESOC validates these solutions through mission-specific scenarios. The project also reflects ESA’s recognition of KP Labs’ expertise and reinforces the importance of collaborative efforts to address the challenges of autonomous systems in space.

KP Labs' previous projects further demonstrate their capabilities. Intuition-1, a 6U satellite launched in November 2023, successfully implemented AI-driven hyperspectral image processing in orbit, reducing data transmission through intelligent filtering of cloud-covered images. Additionally, the LeopardISS experiment, set to launch to the International Space Station as part of Poland's IGNIS mission in May 2025, will validate advanced AI algorithms in space conditions, starting with 3D mapping research for future planetary exploration.

To learn more about the project, visit assurance-ai.space-codev.org, to learn more about KP Labs, visit https://kplabs.space