Adversarial Training for Aerial Disaster Recognition: A Curriculum-Based Defense Against PGD Attacks

Guardado en:
Detalles Bibliográficos
Publicado en:Electronics vol. 14, no. 16 (2025), p. 3210-3225
Autor principal: Kose Kubra
Otros Autores: Zhou, Bing
Publicado:
MDPI AG
Materias:
Acceso en línea:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!

MARC

LEADER 00000nab a2200000uu 4500
001 3244012717
003 UK-CbPIL
022 |a 2079-9292 
024 7 |a 10.3390/electronics14163210  |2 doi 
035 |a 3244012717 
045 2 |b d20250101  |b d20251231 
084 |a 231458  |2 nlm 
100 1 |a Kose Kubra 
245 1 |a Adversarial Training for Aerial Disaster Recognition: A Curriculum-Based Defense Against PGD Attacks 
260 |b MDPI AG  |c 2025 
513 |a Journal Article 
520 3 |a 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. 
653 |a Accuracy 
653 |a Machine learning 
653 |a Deep learning 
653 |a Datasets 
653 |a Performance evaluation 
653 |a Unmanned aerial vehicles 
653 |a Experiments 
653 |a Classification 
653 |a Remote sensing 
653 |a Image classification 
653 |a Diffusion models 
653 |a Remote sensing systems 
653 |a Earthquakes 
653 |a Defense 
653 |a Disasters 
653 |a Monitoring systems 
653 |a Safety critical 
700 1 |a Zhou, Bing 
773 0 |t Electronics  |g vol. 14, no. 16 (2025), p. 3210-3225 
786 0 |d ProQuest  |t Advanced Technologies & Aerospace Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3244012717/abstract/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full Text + Graphics  |u https://www.proquest.com/docview/3244012717/fulltextwithgraphics/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3244012717/fulltextPDF/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch