Enhancing the Transferability of Cross-Domain Adversarial Examples via Region-Aware Generative Perturbation
Open Access
- 24 April 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 2158-2166
Abstract
No abstract availableFunding Information
- the Scientific and Technological Research Program of Chongqing Municipal Education Commission (KJQN202302403)
- the key project of science and technology research program of Chongqing Education Commission of China (KJZD-K202503102)
This publication has 7 references indexed in Scilit:
- Improving Adversarial Transferability via Intermediate-level Perturbation Decay2023
- SA-ES: Subspace Activation Evolution Strategy for Black-Box Adversarial AttacksIEEE Transactions on Emerging Topics in Computational Intelligence, 2022
- A system for identifying an anti-counterfeiting pattern based on the statistical difference in key image regionsExpert Systems with Applications, 2021
- A Self-supervised Approach for Adversarial Robustness2020
- Flower classification using deep convolutional neural networksIET Computer Vision, 2018
- ZOO2017
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015