Fake or Real: The Impostor Hunt in Texts for Space Operations
This addresses AI security threats for space domain applications, but is incremental as it builds on existing competition frameworks and focuses on a specific, emerging problem.
The paper tackles the problem of distinguishing between proper and maliciously modified outputs from Large Language Models in space operations, addressing AI security threats like data poisoning and overreliance, as part of a Kaggle competition to develop new techniques for this under-researched issue.
The "Fake or Real" competition hosted on Kaggle (https://www.kaggle.com/competitions/fake-or-real-the-impostor-hunt ) is the second part of a series of follow-up competitions and hackathons related to the "Assurance for Space Domain AI Applications" project funded by the European Space Agency (https://assurance-ai.space-codev.org/ ). The competition idea is based on two real-life AI security threats identified within the project -- data poisoning and overreliance in Large Language Models. The task is to distinguish between the proper output from LLM and the output generated under malicious modification of the LLM. As this problem was not extensively researched, participants are required to develop new techniques to address this issue or adjust already existing ones to this problem's statement.