AutoMA: Towards Automatic Model Augmentation for Transferable Adversarial Attacks
- 2 November 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 25 (15209210) , 203-213
Abstract
Recent adversarial attack works attempt to improve the transferability by applying various differentiable transformations on input images. Considering the differentiable transformations and the original model together as a new model, these methods can be regarded as model augmentation that effectively derives an ensemble of models from the single original model. Despite their impressive performance, the model augmentation policies used in these methods are manually designed by experimental attempts, leaving the design of model augmentation policy an open question. In this paper, we propose an Automatic Model Augmentation (AutoMA) approach to find a strong model augmentation policy for transferable adversarial attacks. Specifically, we design a discrete search space that contains various diffierentiable transformations with different parameters and adopt reinforcement learning to search for the strong augmentation policy. The sampled augmentation policies together with the rewards they obtain during the searching process reveal several valuable observations for designing more powerful attacks using model augmentation policy: 1) Augmentation transformations on color space are less effective; 2) The transformation type diversity matters; 3) Using small distortion for geometric transformations while larger distortion for intensity transformations. Extensive experiments show that the augmentation policy found by AutoMA achieves superior performance than existing manually designed policies in a wide range of cases.Keywords
Funding Information
- National Natural Science Foundation of China (62002336, U20B2047)
- SenseTime Research Fund for Young Scholars
This publication has 38 references indexed in Scilit:
- Aggregated Residual Transformations for Deep Neural Networks2017
- Towards Evaluating the Robustness of Neural Networks2017
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Identity Mappings in Deep Residual Networks2016
- Deep Residual Learning for Image Recognition2016
- Rethinking the Inception Architecture for Computer Vision2016
- You Only Look Once: Unified, Real-Time Object Detection2016
- Fully convolutional networks for semantic segmentation2015
- Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories2005
- Long Short-Term MemoryNeural Computation, 1997