Trojan horse hunt in deep forecasting models: Insights from the European Space Agency competition
This addresses a security problem for safety-critical applications like space operations, but it is incremental as it builds on existing concerns about backdoor attacks in deep learning.
The paper tackled the security risk of trojan horse attacks in deep forecasting models for space operations by organizing a competition where over 200 teams identified hidden triggers in spacecraft telemetry models, resulting in publicly available benchmark materials and insights for trigger detection in time series forecasting.
Forecasting plays a crucial role in modern safety-critical applications, such as space operations. However, the increasing use of deep forecasting models introduces a new security risk of trojan horse attacks, carried out by hiding a backdoor in the training data or directly in the model weights. Once implanted, the backdoor is activated by a specific trigger pattern at test time, causing the model to produce manipulated predictions. We focus on this issue in our \textit{Trojan Horse Hunt} data science competition, where more than 200 teams faced the task of identifying triggers hidden in deep forecasting models for spacecraft telemetry. We describe the novel task formulation, benchmark set, evaluation protocol, and best solutions from the competition. We further summarize key insights and research directions for effective identification of triggers in time series forecasting models. All materials are publicly available on the official competition webpage https://www.kaggle.com/competitions/trojan-horse-hunt-in-space.