Trojan Horse Hunt in Time Series Forecasting for Space Operations
Krzysztof Kotowski, Ramez Shendy, Jakub Nalepa, Przemys{\l}aw Biecek, Piotr Wilczy\'nski, Agata Kaczmarek, Dawid P{\l}udowski, Artur Janicki, Evridiki Ntagiou

TL;DR
This paper introduces a competition focused on detecting and reconstructing adversarial triggers in satellite telemetry forecasting models, highlighting the importance of AI security in space operations and other safety-critical domains.
Contribution
It presents a novel challenge for identifying triggers in poisoned time series models, providing datasets, baseline methods, and fostering research on AI security in space applications.
Findings
Baseline neural cleanse method is ineffective for time series triggers.
Participants need to develop new approaches for trigger detection.
The competition emphasizes AI security in safety-critical systems.
Abstract
This competition hosted on Kaggle (https://www.kaggle.com/competitions/trojan-horse-hunt-in-space) is the first 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 one of the real-life AI security threats identified within the project -- the adversarial poisoning of continuously fine-tuned satellite telemetry forecasting models. The task is to develop methods for finding and reconstructing triggers (trojans) in advanced models for satellite telemetry forecasting used in safety-critical space operations. Participants are provided with 1) a large public dataset of real-life multivariate satellite telemetry (without triggers), 2) a reference model trained on the clean data, 3) a set of poisoned neural…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsEconomic and Technological Innovation · Big Data and Business Intelligence · Time Series Analysis and Forecasting
MethodsSparse Evolutionary Training
