SentinelAdvMedical: toward adversarial attacks detection on medical image classification via Out-Of-Distribution strategies (2025)
- Authors:
- USP affiliated authors: TRAINA, AGMA JUCI MACHADO - ICMC ; AGUIAR, ERIKSON JÚLIO DE - ICMC
- Unidade: ICMC
- DOI: 10.1117/12.3046951
- Subjects: BANCO DE DADOS MULTIMÍDIA; RECONHECIMENTO DE IMAGEM; APRENDIZAGEM PROFUNDA; SEGURANÇA DE REDES; TOMOGRAFIA DE COERÊNCIA ÓPTICA
- Keywords: Deep Learning; Medical image; Adversarial Attacks; Detecting Attacks; Out-of-Distribution
- Agências de fomento:
- Language: Inglês
- Imprenta:
- Publisher: International Society for Optical Engineering - SPIE
- Publisher place: Bellingham
- Date published: 2025
- Source:
- Título: Proceedings of SPIE
- ISSN: 1605-7422
- Volume/Número/Paginação/Ano: v. 13407, p. 34072U-1-134072U-7, 2025
- Conference titles: SPIE Medical Imaging
- Este periódico é de assinatura
- Este artigo NÃO é de acesso aberto
- Cor do Acesso Aberto: closed
-
ABNT
AGUIAR, Erikson Júlio de e TRAINA, Agma Juci Machado e HELAL, Sumi. SentinelAdvMedical: toward adversarial attacks detection on medical image classification via Out-Of-Distribution strategies. Proceedings of SPIE. Bellingham: International Society for Optical Engineering - SPIE. Disponível em: https://doi.org/10.1117/12.3046951. Acesso em: 28 dez. 2025. , 2025 -
APA
Aguiar, E. J. de, Traina, A. J. M., & Helal, S. (2025). SentinelAdvMedical: toward adversarial attacks detection on medical image classification via Out-Of-Distribution strategies. Proceedings of SPIE. Bellingham: International Society for Optical Engineering - SPIE. doi:10.1117/12.3046951 -
NLM
Aguiar EJ de, Traina AJM, Helal S. SentinelAdvMedical: toward adversarial attacks detection on medical image classification via Out-Of-Distribution strategies [Internet]. Proceedings of SPIE. 2025 ; 13407 34072U-1-134072U-7.[citado 2025 dez. 28 ] Available from: https://doi.org/10.1117/12.3046951 -
Vancouver
Aguiar EJ de, Traina AJM, Helal S. SentinelAdvMedical: toward adversarial attacks detection on medical image classification via Out-Of-Distribution strategies [Internet]. Proceedings of SPIE. 2025 ; 13407 34072U-1-134072U-7.[citado 2025 dez. 28 ] Available from: https://doi.org/10.1117/12.3046951 - MedTimeSplit: continual dataset partitioning to mimic real-world settings for federated learning on Non-IID medical image data
- Security and privacy in machine learning for health systems: strategies and challenges
- RADAR-MIX: how to uncover adversarial attacks in medical image analysis through explainability
- Um framework baseado em blockchain para preservar a privacidade no compartilhamento de dados de saúde
- AI-driven public health surveillance: analyzing vulnerable areas in Brazil using remote sensing and socioeconomic data
- Assessing vulnerabilities of deep learning explainability in medical image analysis under adversarial settings
- Data augmentation for medical image segmentation: a comparative analysis of traditional techniques and synthetic data generation
- DEELE-Rad: exploiting deep radiomics features in deep learning models using COVID-19 chest X-ray images
- Evaluation of the impact of physical adversarial attacks on deep learning models for classifying covid cases
- Análise temporal de municípios produtores de cana-de-açúcar no estado de São Paulo por meio de agrupamento do NDVI (AVHRR/NOAA) e dados de produtividade e área
Informações sobre o DOI: 10.1117/12.3046951 (Fonte: oaDOI API)
Download do texto completo
| Tipo | Nome | Link | |
|---|---|---|---|
 |
3248854.pdf |
How to cite
A citação é gerada automaticamente e pode não estar totalmente de acordo com as normas
