论文标题
神经网络全球鲁棒性认证和培训的工具
A Tool for Neural Network Global Robustness Certification and Training
论文作者
论文摘要
随着对安全至关重要系统中利用机器学习技术的兴趣的增加，外部干扰下的神经网络的鲁棒性引起了越来越多的关注。全局鲁棒性是整个输入域上定义的鲁棒性属性。并且经过认证的全球稳健网络可以确保其在任何可能的网络输入上的稳健性。但是，最先进的全球鲁棒性认证算法只能与最多数千个神经元进行认证。在本文中，我们提出了GPU支持的全球鲁棒性认证框架杂货店，该框架比以前基于优化的认证方法更有效。此外，Grocet提供了可区分的全球鲁棒性，这在全球稳健的神经网络的培训中利用。
With the increment of interest in leveraging machine learning technology in safety-critical systems, the robustness of neural networks under external disturbance receives more and more concerns. Global robustness is a robustness property defined on the entire input domain. And a certified globally robust network can ensure its robustness on any possible network input. However, the state-of-the-art global robustness certification algorithm can only certify networks with at most several thousand neurons. In this paper, we propose the GPU-supported global robustness certification framework GROCET, which is more efficient than the previous optimization-based certification approach. Moreover, GROCET provides differentiable global robustness, which is leveraged in the training of globally robust neural networks.
