# FABLE: A Localized, Targeted Adversarial Attack on Weather Forecasting Models

arXiv: https://arxiv.org/abs/2505.12167 · HTML: https://mlsanity.com/paper/2505.12167/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 43 references that are in the map.
- First posted on arXiv 17 May 2025.

## Builds on (most cited first, 20 of 20)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators](https://mlsanity.com/paper/2202.11214/) (2022)
- [On Evaluating Adversarial Robustness](https://mlsanity.com/paper/1902.06705/) (2019)
- [Adversarial Attacks and Defences: A Survey](https://mlsanity.com/paper/1810.00069/) (2018)
- [Earthformer: Exploring Space-Time Transformers for Earth System Forecasting](https://mlsanity.com/paper/2207.05833/) (2022)
- [Lower Bounds on Adversarial Robustness from Optimal Transport](https://mlsanity.com/paper/1909.12272/) (2019)
- [Prithvi WxC: Foundation Model for Weather and Climate](https://mlsanity.com/paper/2409.13598/) (2024)
- [Conditional Local Convolution for Spatio-temporal Meteorological Forecasting](https://mlsanity.com/paper/2101.01000/) (2021)
- [Practical Adversarial Attacks on Spatiotemporal Traffic Forecasting Models](https://mlsanity.com/paper/2210.02447/) (2022)
- [Efficient Robustness Assessment via Adversarial Spatial-Temporal Focus on Videos](https://mlsanity.com/paper/2301.00896/) (2023)
- [Imperceptible Adversarial Attack via Invertible Neural Networks](https://mlsanity.com/paper/2211.15030/) (2022)
- [Targeted Adversarial Attacks on Wind Power Forecasts](https://mlsanity.com/paper/2303.16633/) (2023)
- [Towards the Worst-case Robustness of Large Language Models](https://mlsanity.com/paper/2501.19040/) (2025)
- [Adversarial Diffusion Attacks on Graph-based Traffic Prediction Models](https://mlsanity.com/paper/2104.09369/) (2021)
- [A Novel Transformer Network with Shifted Window Cross-Attention for Spatiotemporal Weather Forecasting](https://mlsanity.com/paper/2208.01252/) (2022)
- [Adversarial Observations in Weather Forecasting](https://mlsanity.com/paper/2504.15942/) (2025)
- [DeepExtrema: A Deep Learning Approach for Forecasting Block Maxima in Time Series Data](https://mlsanity.com/paper/2205.02441/) (2022)

## Built on by (most cited first, 3 of 3)

- [Adversarial Attacks on Downstream Weather Forecasting Models: Application to Tropical Cyclone Trajectory Prediction](https://mlsanity.com/paper/2510.10140/) (2025)
- [Evaluating Adversarial Attacks on Federated Learning for Temperature Forecasting](https://mlsanity.com/paper/2512.13207/) (2025)
- [Guided Diffusion Sampling for Precipitation Forecast Interventions](https://mlsanity.com/paper/2605.14317/) (2026)

## Abstract (arXiv)

Deep learning-based weather forecasting (DLWF) models have recently demonstrated significant performance gains over gold-standard physics-based simulation tools. However, these models are potentially vulnerable to adversarial attacks, which raises concerns about their trustworthiness. In this paper, we investigate the feasibility and challenges of applying existing adversarial attack methods to DLWF models and propose a novel framework called FABLE (Forecast Alteration By Localized targeted advErsarial attack) to address them. FABLE performs a 3D discrete wavelet decomposition to disentangle the spatial and temporal components of the data. By regulating the magnitude of adversarial perturbations across different components, FABLE produces adversarial inputs that remain closely aligned with the original inputs while steering the DLWF models toward generating the targeted forecast outcomes. Experimental results on real-world weather datasets demonstrate the effectiveness of FABLE over baseline methods across various metrics.