Efficient Adversarial Training with Membership Inference Resistance

Deep cross-media computing faces adversarial example attacks, adversarial training is an effective approach to enhance the robustness of machine learning models via adding adversarial examples into the training phase. However, existing adversarial training methods increase the advantage of membership inference attacks, which aim to determine from the model whether an example is in the training dataset. In this paper, we propose an adversarial training framework that guarantees both robustness and membership privacy by introducing a tailor-made example, called reverse-symmetry example. Moreover, our framework reduces the number of required adversarial examples compared with existing adversarial training methods. We implement the framework based on three adversarial training methods on FMNIST and CIFAR10. The experimental results show that our framework outperforms the original adversarial training with respect to the overall performance of accuracy, robustness, privacy, and runtime.