测试神经程序分析器
Testing Neural Program Analyzers
摘要：
深度神经网络越来越多地用于软件工程和程序分析任务。他们通常采取一个程序，并作出一些预测，例如，bug预测我们称这些模型为神经程序分析器。神经程序的可靠性可能会影响包含分析的可靠性。在本文中，我们描述了我们正在努力开发有效的测试神经程序的技术。我们讨论了开发这些工具所面临的挑战和我们未来的计划。在我们对文献中最近提出的神经模型进行的初步实验中，我们发现该模型非常脆弱，输入中的简单扰动可能导致模型在预测中出错。
英文摘要：
Deep neural networks have been increasingly used in software engineering and program analysis tasks. They usually take a program and make some predictions about it, e.g., bug prediction. We call these models neural program analyzers. The reliability of neural programs can impact the reliability of the encompassing analyses. In this paper, we describe our ongoing efforts to develop effective techniques for testing neural programs. We discuss the challenges involved in developing such tools and our future plans. In our preliminary experiment on a neural model recently proposed in the literature, we found that the model is very brittle, and simple perturbations in the input can cause the model to make mistakes in its prediction.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
