# Trojan horse hunt in deep forecasting models: Insights from the European Space Agency competition

arXiv: https://arxiv.org/abs/2603.20108 · HTML: https://mlsanity.com/paper/2603.20108/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Backdoor and data poisoning attacks, one of 12 directions in LLM safety and security.
- Builds on 17 of its 35 references that are in the map.
- First posted on arXiv 20 Mar 2026.

## Placed in

- LLM safety and security / [Backdoor and data poisoning attacks](https://mlsanity.com/safety/backdoor-and-data-poisoning-attacks/)

## Builds on (most cited first, 17 of 17)

- [Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks](https://mlsanity.com/paper/1805.12185/) (2018)
- [BackdoorBench: A Comprehensive Benchmark of Backdoor Learning](https://mlsanity.com/paper/2206.12654/) (2022)
- [Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks](https://mlsanity.com/paper/2006.12557/) (2020)
- [Darts: User-Friendly Modern Machine Learning for Time Series](https://mlsanity.com/paper/2110.03224/) (2021)
- [BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models](https://mlsanity.com/paper/2408.12798/) (2024)
- [When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated Explanations](https://mlsanity.com/paper/2411.12701/) (2024)
- [European Space Agency Benchmark for Anomaly Detection in Satellite Telemetry](https://mlsanity.com/paper/2406.17826/) (2024)
- [Spacecraft Collision Avoidance Challenge: design and results of a machine learning competition](https://mlsanity.com/paper/2008.03069/) (2020)
- [Backdoor Attacks on Time Series: A Generative Approach](https://mlsanity.com/paper/2211.07915/) (2022)
- [DLP: towards active defense against backdoor attacks with decoupled learning process](https://mlsanity.com/paper/2406.13098/) (2024)
- [Diffusion Theory as a Scalpel: Detecting and Purifying Poisonous Dimensions in Pre-trained Language Models Caused by Backdoor or Bias](https://mlsanity.com/paper/2305.04547/) (2023)
- [Revisiting Backdoor Attacks on Time Series Classification in the Frequency Domain](https://mlsanity.com/paper/2503.09712/) (2025)
- [Backdoor Attack Detection in Computer Vision by Applying Matrix Factorization on the Weights of Deep Networks](https://mlsanity.com/paper/2212.08121/) (2022)
- [TrojanTime: Backdoor Attacks on Time Series Classification](https://mlsanity.com/paper/2502.00646/) (2025)
- [Data Lifecycle Management in Evolving Input Distributions for Learning-based Aerospace Applications](https://mlsanity.com/paper/2209.06855/) (2022)
- [Trojan Horse Hunt in Time Series Forecasting for Space Operations](https://mlsanity.com/paper/2506.01849/) (2025)
- [Verifiable Mission Planning For Space Operations](https://mlsanity.com/paper/2504.11631/) (2025)

## Abstract (arXiv)

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 textitTrojan 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.