mlsanityData to 13 Oct 2026

Fake or Real: The Impostor Hunt in Texts for Space Operations

arXiv 2507.13508 ↗First posted 17 Jul 2025cs.LG cs.CRcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 7 of its 17 references that are in the map. First posted on arXiv 17 Jul 2025.

Builds on

7 of 17 references.

References · 7

  1. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,047
  2. 2020Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performancecited by 399
  3. 2018Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shiftcited by 241
  4. 2022Explanations Can Reduce Overreliance on AI Systems During Decision-Makingcited by 111
  5. 2018Data Poisoning Attacks against Online Learningcited by 27
  6. 2024InterrogateLLM: Zero-Resource Hallucination Detection in LLM-Generated Answerscited by 26
  7. 2020Adversarial Concept Drift Detection under Poisoning Attacks for Robust Data Stream Miningcited by 11

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Trojan horse hunt in deep forecasting models: Insights from the European Space Agency competition
  2. 2025Large Language Models as Autonomous Spacecraft Operators in Kerbal Space Program
  3. 2026Honeyquest for LLMs: Rethinking Cyber Deception for AI Attackers
  4. 2025Deception in LLMs: Self-Preservation and Autonomous Goals in Large Language Models
  5. 2025OCCULT: Evaluating Large Language Models for Offensive Cyber Operation Capabilities
  6. 2026SINGED: Correct Outputs Do Not Certify Safe Execution in LLM Agents
  7. 2024Hacking CTFs with Plain Agents
  8. 2025Could AI Trace and Explain the Origins of AI-Generated Images and Text?