2019/08/17 by Matthew Sotoudeh, Sotoudeh, Matthew, Aditya Thakur +1
Computer Science · #Adversarial Robustness in Machine Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Algorithms #Neural Networks and Applications #Programming Languages (cs.PL)
paper · pdf · doi:10.48550/arxiv.1908.06223
openalex publication_date 2019/08/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Analysis and manipulation of trained neural networks is a challenging and important problem. We propose a symbolic representation for piecewise-linear neural networks and discuss its efficient computation. With this representation, one can translate the problem of analyzing a complex neural network into that of analyzing a finite set of affine functions. We demonstrate the use of this representation for three applications. First, we apply the symbolic representation to computing weakest preconditions on network inputs, which we use to exactly visualize the advisories made by a network meant to operate an aircraft collision avoidance system. Second, we use the symbolic representation to compute strongest postconditions on the network outputs, which we use to perform bounded model checking on standard neural network controllers. Finally, we show how the symbolic representation can be combined with a new form of neural network to perform patching; i.e., correct user-specified behavior of the network.