DIB-UAP: enhancing the transferability of universal adversarial perturbation via deep information bottleneck

Abstract Significant structural differences in DNN-based object detectors hinders the transferability of adversarial attacks. Studies show that intermediate features extracted by the detector contain more model-independent information, and disrupting these features can enhance attack transferability...

Descrición completa

Detalles Bibliográficos

Principais autores:	Yang Wang, Yunfei Zheng, Lei Chen, Zhen Yang, Tieyong Cao
Formato:	Artigo
Idioma:	Inglês
Publicado:	Springer 2024-06-01
Series:	Complex & Intelligent Systems
Assuntos:	Adversarial attack Universal adversarial perturbation Attack transferability Neural network robustness
Acceso en liña:	https://doi.org/10.1007/s40747-024-01522-z
Tags:	Engadir etiqueta Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!