Improving adversarial transferability through hybrid augmentation

Peican Zhu; Zepeng Fan; Sensen Guo; Keke Tang; Xingyu Li

doi:10.1016/j.cose.2023.103674

ScienceGate Book Chapters

JOURNAL ARTICLE

Improving adversarial transferability through hybrid augmentation

Peican Zhu Zepeng Fan Sensen Guo Keke Tang Xingyu Li

Year: 2023 Journal: Computers & Security Vol: 139 Pages: 103674-103674 Publisher: Elsevier BV

DOI: 10.1016/j.cose.2023.103674

Get Full-Text PDF Get Analytical Report

Keywords:

Transferability Computer science Adversarial system Domain (mathematical analysis) Focus (optics) Masking (illustration) Artificial intelligence Diversity (politics) Scaling Frequency domain Image (mathematics) Machine learning Pattern recognition (psychology) Algorithm Computer vision Mathematics

Metrics

Cited By

3.83

FWCI (Field Weighted Citation Impact)

Refs

0.93

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Citation History

Topics

Adversarial Robustness in Machine Learning

Physical Sciences → Computer Science → Artificial Intelligence

Advanced Neural Network Applications

Physical Sciences → Computer Science → Computer Vision and Pattern Recognition

Anomaly Detection Techniques and Applications

Physical Sciences → Computer Science → Artificial Intelligence

Improving adversarial transferability through hybrid augmentation

Metrics

Citation History

Topics

Related Documents

Improving the Transferability of Adversarial Examples by Feature Augmentation

Boosting Adversarial Transferability through Augmentation in Hypothesis Space

Improving adversarial transferability through frequency enhanced momentum

Improving transferability of adversarial examples by saliency distribution and data augmentation

Improving the transferability of adversarial examples through neighborhood attribution