Journal
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
Volume -, Issue -, Pages 14963-14972Publisher
IEEE COMPUTER SOC
DOI: 10.1109/CVPR52688.2022.01456
Keywords
-
Funding
- National Natural Science Foundation of China [62076105]
- Hubei International Cooperation Foundation of China [2021EHB011]
Ask authors/readers for more resources
The black-box adversarial attack is a practical tool in deep learning security that is used to attack target models without accessing their network architecture or internal weights. In this paper, a novel attack method called SVRE is proposed, which reduces the gradient variance of ensemble models to improve attack effectiveness. Empirical results on ImageNet dataset show promising performance of the proposed method.
The black-box adversarial attack has attracted impressive attention for its practical use in the field of deep learning security. Meanwhile, it is very challenging as there is no access to the network architecture or internal weights of the target model. Based on the hypothesis that if an example remains adversarial for multiple models, then it is more likely to transfer the attack capability to other models, the ensemble-based adversarial attack methods are efficient and widely used for black-box attacks. However, ways of ensemble attack are rather less investigated, and existing ensemble attacks simply fuse the outputs of all the models evenly. In this work, we treat the iterative ensemble attack as a stochastic gradient descent optimization process, in which the variance of the gradients on different models may lead to poor local optima. To this end, we propose a novel attack method called the stochastic variance reduced ensemble (SVRE) attack, which could reduce the gradient variance of the ensemble models and take full advantage of the ensemble attack. Empirical results on the standard ImageNet dataset demonstrate that the proposed method could boost the adversarial transferability and outperforms existing ensemble attacks significantly. Code is available at https://github.com/JHL-HUST/SVRE.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available