IBD: An Interpretable Backdoor-Detection Method via Multivariate Interactions

Recent work has shown that deep neural networks are vulnerable to backdoor attacks. In comparison with the success of backdoor-attack methods, existing backdoor-defense methods face a lack of theoretical foundations and interpretable solutions. Most defense methods are based on experience with the c...

Descripción completa

Detalles Bibliográficos
Autores principales: Xu, Yixiao, Liu, Xiaolei, Ding, Kangyi, Xin, Bangzhou
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9695053/
https://www.ncbi.nlm.nih.gov/pubmed/36433292
http://dx.doi.org/10.3390/s22228697

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9695053/
https://www.ncbi.nlm.nih.gov/pubmed/36433292
http://dx.doi.org/10.3390/s22228697

Ejemplares similares