mlsanityData to 14 Oct 2026

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

arXiv 2505.12167 ↗First posted 17 May 2025cs.LG cs.CRcited by 3

Not on the map. Why?

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.

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

20 of 43 references.

References · 20

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2016Adversarial examples in the physical worldcited by 1,769
  5. 2022FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operatorscited by 776
  6. 2019On Evaluating Adversarial Robustnesscited by 447
  7. 2018Adversarial Attacks and Defences: A Surveycited by 259
  8. 2022Earthformer: Exploring Space-Time Transformers for Earth System Forecastingcited by 152
  9. 2019Lower Bounds on Adversarial Robustness from Optimal Transportcited by 53
  10. 2024Prithvi WxC: Foundation Model for Weather and Climatecited by 31
  11. 2021Conditional Local Convolution for Spatio-temporal Meteorological Forecastingcited by 30
  12. 2022Practical Adversarial Attacks on Spatiotemporal Traffic Forecasting Modelscited by 29
8 more
  1. 2023Efficient Robustness Assessment via Adversarial Spatial-Temporal Focus on Videoscited by 20
  2. 2022Imperceptible Adversarial Attack via Invertible Neural Networkscited by 12
  3. 2023Targeted Adversarial Attacks on Wind Power Forecastscited by 9
  4. 2025Towards the Worst-case Robustness of Large Language Modelscited by 7
  5. 2021Adversarial Diffusion Attacks on Graph-based Traffic Prediction Modelscited by 5
  6. 2022A Novel Transformer Network with Shifted Window Cross-Attention for Spatiotemporal Weather Forecastingcited by 5
  7. 2025Adversarial Observations in Weather Forecastingcited by 4
  8. 2022DeepExtrema: A Deep Learning Approach for Forecasting Block Maxima in Time Series Datacited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025Adversarial Attacks on Downstream Weather Forecasting Models: Application to Tropical Cyclone Trajectory Predictioncited by 1
  2. 2025Evaluating Adversarial Attacks on Federated Learning for Temperature Forecastingcited by 0
  3. 2026Guided Diffusion Sampling for Precipitation Forecast Interventionscited by 0