mlsanityData to 14 Oct 2026

Adversarial Observations in Weather Forecasting

arXiv 2504.15942 ↗First posted 22 Apr 2025cs.CR cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

AI-based systems, such as Google's GenCast, have recently redefined the state of the art in weather forecasting, offering more accurate and timely predictions of both everyday weather and extreme events. While these systems are on the verge of replacing traditional meteorological methods, they also introduce new vulnerabilities into the forecasting process. In this paper, we investigate this threat and present a novel attack on autoregressive diffusion models, such as those used in GenCast, capable of manipulating weather forecasts and fabricating extreme events, including hurricanes, heat waves, and intense rainfall. The attack introduces subtle perturbations into weather observations that are statistically indistinguishable from natural noise and change less than 0.1% of the measurements - comparable to tampering with data from a single meteorological satellite. As modern forecasting integrates data from nearly a hundred satellites and many other sources operated by different countries, our findings highlight a critical security risk with the potential to cause large-scale disruptions and undermine public trust in weather prediction.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 11 of its 39 references that are in the map. First posted on arXiv 22 Apr 2025.

Builds on

11 of 39 references.

References · 11

  1. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  2. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  3. 2016Adversarial examples in the physical worldcited by 1,769
  4. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  5. 2023Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examplescited by 167
  6. 2024DiffDA: a Diffusion Model for Weather-scale Data Assimilationcited by 61
  7. 2019Exploiting Vulnerabilities of Load Forecasting Through Adversarial Attackscited by 18
  8. 2024Diffusion Policy Attacker: Crafting Adversarial Attacks for Diffusion-based Policiescited by 18
  9. 2023Targeted Adversarial Attacks on Wind Power Forecastscited by 9
  10. 2021Estimating Solar and Wind Power Production using Computer Vision Deep Learning Techniques on Weather Mapscited by 2
  11. 2023Theoretically Principled Trade-off for Stateful Defenses against Query-Based Black-Box Attackscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025FABLE: A Localized, Targeted Adversarial Attack on Weather Forecasting Modelscited by 3
  2. 2025Adversarial Attacks on Downstream Weather Forecasting Models: Application to Tropical Cyclone Trajectory Predictioncited by 1
  3. 2025Evaluating Adversarial Attacks on Federated Learning for Temperature Forecastingcited by 0
  4. 2026Guided Diffusion Sampling for Precipitation Forecast Interventionscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024BACKTIME: Backdoor Attacks on Multivariate Time Series Forecasting
  2. 2023Precipitation nowcasting with generative diffusion models
  3. 2023SEEDS: Emulation of Weather Forecast Ensembles with Diffusion Models
  4. 2025Data-Efficient Ensemble Weather Forecasting with Diffusion Models
  5. 2024Kilometer-Scale Convection Allowing Model Emulation using Generative Diffusion Modeling
  6. 2024Four-hour thunderstorm nowcasting using a deep diffusion model of satellite data
  7. 2026Machine learning is revolutionizing weather forecasting -- the next step is a change in how we work ↗
  8. 2025LaDCast: A Latent Diffusion Model for Medium-Range Ensemble Weather Forecasting