Content area

Abstract

Unmanned aerial vehicles (UAVs) play an ever-increasing role in disaster response and remote sensing. However, the deep learning models they rely on remain highly vulnerable to adversarial attacks. This paper presents an evaluation and defense framework aimed at enhancing adversarial robustness in aerial disaster image classification using the AIDERV2 dataset. Our methodology is structured into the following four phases: (I) baseline training with clean data using ResNet-50, (II) vulnerability assessment under Projected Gradient Descent (PGD) attacks, (III) adversarial training with PGD to improve model resilience, and (IV) comprehensive post-defense evaluation under identical attack scenarios. The baseline model achieves 93.25% accuracy on clean data but drops to as low as 21.00% under strong adversarial perturbations. In contrast, the adversarially trained model maintains over 75.00% accuracy across all PGD configurations, reducing the attack success rate by more than 60%. We introduce metrics, such as Clean Accuracy, Adversarial Accuracy, Accuracy Drop, and Attack Success Rate, to evaluate defense performance. Our results show the practical importance of adversarial training for safety-critical UAV applications and provide a reference point for future research. This work contributes to making deep learning systems on aerial platforms more secure, robust, and reliable in mission-critical environments.

Details

1009240
Business indexing term
Title
Adversarial Training for Aerial Disaster Recognition: A Curriculum-Based Defense Against PGD Attacks
Author
Publication title
Volume
14
Issue
16
First page
3210
Number of pages
16
Publication year
2025
Publication date
2025
Publisher
MDPI AG
Place of publication
Basel
Country of publication
Switzerland
Publication subject
e-ISSN
20799292
Source type
Scholarly Journal
Language of publication
English
Document type
Journal Article
Publication history
 
 
Online publication date
2025-08-13
Milestone dates
2025-07-24 (Received); 2025-08-11 (Accepted)
Publication history
 
 
   First posting date
13 Aug 2025
ProQuest document ID
3244012717
Document URL
https://www.proquest.com/scholarly-journals/adversarial-training-aerial-disaster-recognition/docview/3244012717/se-2?accountid=208611
Copyright
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Last updated
2025-08-29
Database
ProQuest One Academic