SA-ES: Subspace Activation Evolution Strategy for Black-Box Adversarial Attacks
- 28 October 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 7 (3) , 780-790
Abstract
Deep neural networks are vulnerable to adversarial examples that alter the output significantly with imperceptible change in the input. In our black-box setting, the adversarial attacker can only query the model to predict the value after the softmax layer without accessing the underlying model. Currently, generating adversarial examples with high qualifications in the query-limited setting and investigating the distribution of adversarial examples are two main challenges in the black-box attack. In this paper, we propose a zeroth-order optimization method for the black-box adversarial attack, termed subspace activation evolution strategy (SA-ES). It captures the most promising direction for generating more convincing adversarial examples.Moreover, instead of only searching for one reliable adversarial example for an original input, SA-ES finds a distribution of adversarial examples, such that a sample drawn from this distribution is likely an adversarial example. We conduct comprehensive experiments on various data sets and validate that the proposed algorithm can efficiently find perturbation-sensitive regions of an image and stably explore the distribution of adversarial examples with the limited query, and outperforms the existing methods. In addition, we apply SA-ES to physical reality black-box attacks, which effectively generate simulated physical adversarial examples for the adversarial training model.Keywords
Funding Information
- National Natural Science Foundation of China (62102178, 62072234, 62125302, 61732006)
- Natural Science Foundation of Jiangsu Province of China (BK20200443, BK20181288)
This publication has 23 references indexed in Scilit:
- Empirical Study of the Topology and Geometry of Deep Networks2018
- Robust Physical-World Attacks on Deep Learning Visual Classification2018
- A Simple Yet Efficient Evolution Strategy for Large-Scale Black-Box OptimizationIEEE Transactions on Evolutionary Computation, 2017
- Towards Evaluating the Robustness of Neural Networks2017
- Practical Black-Box Attacks against Machine Learning2017
- DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks2016
- Accessorize to a Crime2016
- Deep Residual Learning for Image Recognition2016
- A Multi-View Deep Learning Approach for Cross Domain User Modeling in Recommendation Systems2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015