论文标题
重复神经网络的财产定向验证
Property-Directed Verification of Recurrent Neural Networks
论文作者
论文摘要
本文提出了一种以财产为导向的方法来验证经常性神经网络（RNN）。为此，我们使用主动自动机学习从给定的RNN学习确定性有限自动机作为替代模型。然后可以使用模型检查作为验证技术来分析此模型。属性定向一词反映了我们的过程由给定属性指导和控制的想法，而不是单独执行两个步骤。我们表明，这不仅使我们能够快速发现小型反例，而且还可以通过向RNN中的基本错误倾斜的流动来概括它们来概括它们。
This paper presents a property-directed approach to verifying recurrent neural networks (RNNs). To this end, we learn a deterministic finite automaton as a surrogate model from a given RNN using active automata learning. This model may then be analyzed using model checking as verification technique. The term property-directed reflects the idea that our procedure is guided and controlled by the given property rather than performing the two steps separately. We show that this not only allows us to discover small counterexamples fast, but also to generalize them by pumping towards faulty flows hinting at the underlying error in the RNN.
