Adversarial Robustness for Deep Learning-based Wildfire Prediction Models

TL;DR

This paper introduces WARP, a model-agnostic framework for evaluating and improving the adversarial robustness of deep learning models in wildfire smoke detection, addressing data limitations and model vulnerabilities.

Contribution

The paper presents WARP, the first framework for assessing adversarial robustness in wildfire detection models, and proposes data augmentation techniques to enhance their resilience.

Findings

Transformers showed over 70% precision degradation under global attacks.

Both CNNs and transformers struggled to distinguish smoke from cloud-like patches.

Proposed data augmentation improved model robustness and accuracy.

Abstract

Rapidly growing wildfires have recently devastated societal assets, exposing a critical need for early warning systems to expedite relief efforts. Smoke detection using camera-based Deep Neural Networks (DNNs) offers a promising solution for wildfire prediction. However, the rarity of smoke across time and space limits training data, raising model overfitting and bias concerns. Current DNNs, primarily Convolutional Neural Networks (CNNs) and transformers, complicate robustness evaluation due to architectural differences. To address these challenges, we introduce WARP (Wildfire Adversarial Robustness Procedure), the first model-agnostic framework for evaluating wildfire detection models' adversarial robustness. WARP addresses inherent limitations in data diversity by generating adversarial examples through image-global and -local perturbations. Global and local attacks superimpose Gaussian noise and PNG patches onto image inputs, respectively; this suits both CNNs and transformers while generating realistic adversarial scenarios. Using WARP, we assessed real-time CNNs and Transformers, uncovering key vulnerabilities. At times, transformers exhibited over 70% precision degradation under global attacks, while both models generally struggled to differentiate cloud-like PNG patches from real smoke during local attacks. To enhance model robustness, we proposed four wildfire-oriented data augmentation techniques based on WARP's methodology and results, which diversify smoke image data and improve model precision and robustness. These advancements represent a substantial step toward developing a reliable early wildfire warning system, which may be our first safeguard against wildfire destruction.