论文标题
学习任务意识强大的深度学习系统
Learning Task-aware Robust Deep Learning Systems
论文作者
论文摘要
许多作品表明，深度学习系统容易受到对抗性攻击的影响。深度学习系统由两个部分组成：深度学习任务和深层模型。如今，大多数现有作品都研究了深度学习系统鲁棒性的影响，而忽略了学习任务的影响。在本文中，我们采用二进制和间隔标签编码策略来重新定义分类任务和设计相应的损失，以提高深度学习系统的鲁棒性。我们的方法可以看作是从学习任务和深层模型中改善深度学习系统的鲁棒性。实验结果表明，我们的学习任务感知方法比传统分类更强大，同时保持准确性。
Many works demonstrate that deep learning system is vulnerable to adversarial attack. A deep learning system consists of two parts: the deep learning task and the deep model. Nowadays, most existing works investigate the impact of the deep model on robustness of deep learning systems, ignoring the impact of the learning task. In this paper, we adopt the binary and interval label encoding strategy to redefine the classification task and design corresponding loss to improve robustness of the deep learning system. Our method can be viewed as improving the robustness of deep learning systems from both the learning task and deep model. Experimental results demonstrate that our learning task-aware method is much more robust than traditional classification while retaining the accuracy.
