Verifying Recurrent Neural Networks using Invariant Inference

Autor:	Jacoby, Yuval, Barrett, Clark, Katz, Guy
Rok vydání:	2020
Předmět:	Computer Science - Artificial Intelligence Computer Science - Logic in Computer Science
Druh dokumentu:	Working Paper
Popis:	Deep neural networks are revolutionizing the way complex systems are developed. However, these automatically-generated networks are opaque to humans, making it difficult to reason about them and guarantee their correctness. Here, we propose a novel approach for verifying properties of a widespread variant of neural networks, called recurrent neural networks. Recurrent neural networks play a key role in, e.g., natural language processing, and their verification is crucial for guaranteeing the reliability of many critical systems. Our approach is based on the inference of invariants, which allow us to reduce the complex problem of verifying recurrent networks into simpler, non-recurrent problems. Experiments with a proof-of-concept implementation of our approach demonstrate that it performs orders-of-magnitude better than the state of the art. Comment: This is the extended version of a paper with the same title that appeared at ATVA 2020
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2004.02462 Zobrazit plný text záznamu View this record from Arxiv