Efficient black-box attack with surrogate models and multiple universal adversarial perturbations

Abstract Deep learning models are inherently vulnerable to adversarial examples, particularly in black-box settings where attackers have limited knowledge of the target model. Existing attack algorithms often face challenges in balancing effectiveness and efficiency. Adversarial perturbations genera...

Full description

Saved in:
Bibliographic Details
Main Authors: Tao Ma, Hong Zhao, Ling Tang, Mingsheng Xue, Jing Liu
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-87529-z
Tags: Add Tag
No Tags, Be the first to tag this record!