Adversarial Examples Detection With Bayesian Neural Network
Yao Li, Tongyi Tang, Cho‐Jui Hsieh, Thomas C. M. Lee · IEEE Transactions on Emerging Topics in Computational Intelligence · 2024
In this paper, we propose a new framework to detect adversarial examples motivated by the observations that random components can improve the smoothness of predictors and make it easier to simulate the output distribution of a deep neural network. With these observations, we propose a novel Bayesian adversarial example detector, short forBATer, to improve the performance of adversarial example detection. Specifically, we study the distributional difference of hidden layer output between natural and adversarial examples, and propose to use the randomness of the Bayesian neural network to simulate hidden layer output distribution and leverage the distribution dispersion to detect adversarial examples. The advantage of a Bayesian neural network is that the output is stochastic while a deep neural network without random components does not have such characteristics. Empirical results on several benchmark datasets against popular attacks show that the proposedBATeroutperforms the state-of-the-art detectors in adversarial example detection.