Open Access

ARTICLE

SAMI-FGSM: Towards Transferable Attacks with Stochastic Gradient Accumulation

Haolang Feng^1,2, Yuling Chen^1,2,*, Yang Huang^1,2, Xuewei Wang³, Haiwei Sang⁴

1 State Key Laboratory of Public Big Data, Guizhou University, Guiyang, 550025, China
2 College of Computer Science and Technology, Guizhou University, Guiyang, 550025, China
3 Computer College, Weifang University of Science and Technology, Weifang, 262700, China
4 School of Mathematics and Big Data, Guizhou Education University, Guiyang, 550018, China

* Corresponding Author: Yuling Chen. Email:

Computers, Materials & Continua 2025, 84(3), 4469-4490. https://doi.org/10.32604/cmc.2025.064896

Received 26 February 2025; Accepted 22 May 2025; Issue published 30 July 2025

Abstract

Deep neural networks remain susceptible to adversarial examples, where the goal of an adversarial attack is to introduce small perturbations to the original examples in order to confuse the model without being easily detected. Although many adversarial attack methods produce adversarial examples that have achieved great results in the white-box setting, they exhibit low transferability in the black-box setting. In order to improve the transferability along the baseline of the gradient-based attack technique, we present a novel Stochastic Gradient Accumulation Momentum Iterative Attack (SAMI-FGSM) in this study. In particular, during each iteration, the gradient information is calculated using a normal sampling approach that randomly samples around the sample points, with the highest probability of capturing adversarial features. Meanwhile, the accumulated information of the sampled gradient from the previous iteration is further considered to modify the current updated gradient, and the original gradient attack direction is changed to ensure that the updated gradient direction is more stable. Comprehensive experiments conducted on the ImageNet dataset show that our method outperforms existing state-of-the-art gradient-based attack techniques, achieving an average improvement of 10.2% in transferability.

---

Keywords

---