Adversarial robustness and attacks for multi-view deep models.

Recent work has highlighted the vulnerability of many deep machine learning models to adversarial examples. It attracts increasing attention to adversarial attacks, which can be used to evaluate the security and robustness of models before they are deployed. However, to our best knowledge, there is no specific research on the adversarial robustness and attacks for multi-view deep models. Based on the fact that adversarial examples generalize well among different models, this paper takes the adversarial attack on the multi-view convolutional neural network as an example to investigate the adversarial robustness of multi-view deep models, and further proposes effective multi-view adversarial attacks. This paper proposes two strategies, two-stage attack (TSA) and end-to-end attack (ETEA), to attack against well-trained multi-view models. With the mild assumption that the single-view model on which the target multi-view model is based is known, we first propose the TSA strategy. The main idea of TSA is to attack the multi-view model with adversarial examples generated by attacking the associated single-view model, by which state-of-the-art single-view attack methods are directly extended to the multi-view scenario. Then we further propose the ETEA strategy where the multi-view model is provided publicly. The ETEA is applied to accomplish direct attacks on the target multi-view model, where we develop three effective multi-view attack methods. Extensive experimental results show that multi-view models are more robust than single-view models and demonstrate the effectiveness of the proposed multi-view adversarial attacks. [ABSTRACT FROM AUTHOR]