Robust Ensemble Model Training via Random Layer Sampling Against Adversarial Attack
This addresses security and medical application concerns by enhancing model robustness against adversarial attacks, though it appears incremental as it builds on existing ensemble and sampling techniques.
The paper tackles the vulnerability of deep neural networks to adversarial examples by proposing an ensemble training framework with random layer sampling, which improves adversarial robustness as demonstrated in experiments on three datasets.
Deep neural networks have achieved substantial achievements in several computer vision areas, but have vulnerabilities that are often fooled by adversarial examples that are not recognized by humans. This is an important issue for security or medical applications. In this paper, we propose an ensemble model training framework with random layer sampling to improve the robustness of deep neural networks. In the proposed training framework, we generate various sampled model through the random layer sampling and update the weight of the sampled model. After the ensemble models are trained, it can hide the gradient efficiently and avoid the gradient-based attack by the random layer sampling method. To evaluate our proposed method, comprehensive and comparative experiments have been conducted on three datasets. Experimental results show that the proposed method improves the adversarial robustness.