论文标题
通过随机层采样对抗攻击，可靠的合奏模型训练
Robust Ensemble Model Training via Random Layer Sampling Against Adversarial Attack
论文作者
论文摘要
深度神经网络在几个计算机视觉领域取得了实质性成就，但是脆弱性通常被人类认可的对抗性例子所欺骗。这是安全或医疗应用程序的重要问题。在本文中，我们提出了一个带有随机层采样的集成模型训练框架，以改善深神经网络的鲁棒性。在提出的训练框架中，我们通过随机层采样生成各种采样模型，并更新采样模型的重量。在训练集合模型之后，它可以有效地隐藏梯度，并通过随机层采样方法避免基于梯度的攻击。为了评估我们提出的方法，在三个数据集上进行了全面和比较实验。实验结果表明，所提出的方法改善了对抗性鲁棒性。
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.
