Enhancing adversarial transferability by resolving gradient conflicts in multi-input transformations
Authors:
- Desheng ZhengDZDesheng Zheng
- Ye TianYTYe Tian
- Yong ZhouYZYong Zhou
- Yaoxin DuanYDYaoxin Duan
- Fan MinFMFan Min
- Wuping KeWKWuping Ke
- 6 December 2025
- journal article
- Published by Elsevier in Applied Soft Computing
- Vol. 188
Abstract
No abstract availableFunding Information
- Natural Science Foundation of Xinjiang Uygur Autonomous Region (2024D01A20)
- Key Laboratory of Industrial Internet of Things and Networked Control, Ministry of Education (2022FF02)
This publication has 5 references indexed in Scilit:
- Frequency-domain augmentation and multi-scale feature alignment for improving transferability of adversarial examplesComputer Networks, 2025
- Improving the transferability of adversarial examples through semantic-mixup inputsKnowledge-Based Systems, 2025
- Frequency-based methods for improving the imperceptibility and transferability of adversarial examplesApplied Soft Computing, 2023
- AutoMA: Towards Automatic Model Augmentation for Transferable Adversarial AttacksIEEE Transactions on Multimedia, 2021
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015