Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial Examples
This addresses the challenge of black-box adversarial attacks for security researchers, though it is incremental as it builds on existing methods with a novel model diversity approach.
The paper tackles the problem of improving the transferability of adversarial examples across deep neural networks by attacking a Bayesian model instead of increasing input diversity, resulting in a roughly 19% absolute increase in average attack success rate on ImageNet compared to recent state-of-the-art methods.
The transferability of adversarial examples across deep neural networks (DNNs) is the crux of many black-box attacks. Many prior efforts have been devoted to improving the transferability via increasing the diversity in inputs of some substitute models. In this paper, by contrast, we opt for the diversity in substitute models and advocate to attack a Bayesian model for achieving desirable transferability. Deriving from the Bayesian formulation, we develop a principled strategy for possible finetuning, which can be combined with many off-the-shelf Gaussian posterior approximations over DNN parameters. Extensive experiments have been conducted to verify the effectiveness of our method, on common benchmark datasets, and the results demonstrate that our method outperforms recent state-of-the-arts by large margins (roughly 19% absolute increase in average attack success rate on ImageNet), and, by combining with these recent methods, further performance gain can be obtained. Our code: https://github.com/qizhangli/MoreBayesian-attack.