Related references
Note: Only part of the references are listed.
Article
Computer Science, Information Systems
Boosting adversarial attacks with transformed gradient
Zhengyun He et al.
Summary: This study proposes a Transformed Gradient method, which achieves a higher attack success rate with lower perturbations against an ensemble of black-box defense models through original gradient accumulation, gradient amplification, and gradient truncation. By optimizing coefficients of the source-model ensemble and introducing new evaluation metrics, it outperforms existing methods in generating adversarial examples.
COMPUTERS & SECURITY (2022)
Article
Computer Science, Information Systems
Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey
Naveed Akhtar et al.
IEEE ACCESS (2018)
Article
Computer Science, Artificial Intelligence
ImageNet Large Scale Visual Recognition Challenge
Olga Russakovsky et al.
INTERNATIONAL JOURNAL OF COMPUTER VISION (2015)