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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Deng, Yue, Galib, Asadullah Hill, Lan, Xin, Gunn, Jack, Tan, Pang-Ning, Luo, Lifeng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910101539913728
author Deng, Yue
Galib, Asadullah Hill
Lan, Xin
Gunn, Jack
Tan, Pang-Ning
Luo, Lifeng
author_facet Deng, Yue
Galib, Asadullah Hill
Lan, Xin
Gunn, Jack
Tan, Pang-Ning
Luo, Lifeng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_12167
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FABLE: A Localized, Targeted Adversarial Attack on Weather Forecasting Models
Deng, Yue
Galib, Asadullah Hill
Lan, Xin
Gunn, Jack
Tan, Pang-Ning
Luo, Lifeng
Machine Learning
Cryptography and Security
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.
title FABLE: A Localized, Targeted Adversarial Attack on Weather Forecasting Models
topic Machine Learning
Cryptography and Security
url https://arxiv.org/abs/2505.12167