论文标题
使用有限自动机验证和解释神经网络
Verifying And Interpreting Neural Networks using Finite Automata
论文作者
论文摘要
鉴于它们在应用程序中的无处不在，包括安全性及其黑盒性质，验证属性并解释深神经网络（DNN）的行为是一项重要任务。我们提出了一种自动化方法，以解决DNN分析中引起的问题。我们表明，DNN的投入输出行为可以通过（特殊的）弱的Büchi自动机精确捕获，我们展示了如何使用这些行为来解决DNN的常见验证和解释任务，例如对抗性鲁棒性或最低足够的原因。
Verifying properties and interpreting the behaviour of deep neural networks (DNN) is an important task given their ubiquitous use in applications, including safety-critical ones, and their black-box nature. We propose an automata-theoric approach to tackling problems arising in DNN analysis. We show that the input-output behaviour of a DNN can be captured precisely by a (special) weak Büchi automaton and we show how these can be used to address common verification and interpretation tasks of DNN like adversarial robustness or minimum sufficient reasons.
