论文标题
反复神经网络的可扩展性多面体验证
Scalable Polyhedral Verification of Recurrent Neural Networks
论文作者
论文摘要
We present a scalable and precise verifier for recurrent neural networks, called Prover based on two novel ideas: (i) a method to compute a set of polyhedral abstractions for the non-convex and nonlinear recurrent update functions by combining sampling, optimization, and Fermat's theorem, and (ii) a gradient descent based algorithm for abstraction refinement guided by the certification problem that combines multiple abstractions for每个神经元。使用Prover，我们介绍了对复发性神经网络的非平凡用例，即语音分类的第一个研究。为了实现这一目标，我们还为非线性语音预处理管道开发了自定义抽象。我们的评估表明，Prover成功地验证了计算机视觉，语音和运动传感器数据分类中的几个具有挑战性的经常性模型，超出了先前工作的范围。
We present a scalable and precise verifier for recurrent neural networks, called Prover based on two novel ideas: (i) a method to compute a set of polyhedral abstractions for the non-convex and nonlinear recurrent update functions by combining sampling, optimization, and Fermat's theorem, and (ii) a gradient descent based algorithm for abstraction refinement guided by the certification problem that combines multiple abstractions for each neuron. Using Prover, we present the first study of certifying a non-trivial use case of recurrent neural networks, namely speech classification. To achieve this, we additionally develop custom abstractions for the non-linear speech preprocessing pipeline. Our evaluation shows that Prover successfully verifies several challenging recurrent models in computer vision, speech, and motion sensor data classification beyond the reach of prior work.
