Diverse Knowledge Distillation (DKD): A Solution for Improving The Robustness of Ensemble Models Against Adversarial Attacks
This addresses the problem of adversarial vulnerability in ensemble models for image classification, offering an incremental enhancement over existing methods.
The paper tackled improving the robustness of ensemble models against adversarial attacks by training each member to learn distinct latent spaces, achieving security and performance improvements on CIFAR10 and MNIST datasets compared to state-of-the-art defenses.
This paper proposes an ensemble learning model that is resistant to adversarial attacks. To build resilience, we introduced a training process where each member learns a radically distinct latent space. Member models are added one at a time to the ensemble. Simultaneously, the loss function is regulated by a reverse knowledge distillation, forcing the new member to learn different features and map to a latent space safely distanced from those of existing members. We assessed the security and performance of the proposed solution on image classification tasks using CIFAR10 and MNIST datasets and showed security and performance improvement compared to the state of the art defense methods.