Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

11-2019

Abstract

Recurrent neural network (RNN) has achieved great success in processing sequential inputs for applications such as automatic speech recognition, natural language processing and machine translation. However, quality and reliability issues of RNNs make them vulnerable to adversarial attacks and hinder their deployment in real-world applications. In this paper, we propose a quantitative analysis framework — DeepStellar— to pave the way for effective quality and security analysis of software systems powered by RNNs. DeepStellar is generic to handle various RNN architectures, including LSTM and GRU, scalable to work on industrial-grade RNN models, and extensible to develop customized analyzers and tools. We demonstrated that, with DeepStellar, users are able to design efficient test generation tools, and develop effective adversarial sample detectors. We tested the developed applications on three real RNN models, including speech recognition and image classification. DeepStellar outperforms existing approaches three hundred times in generating defect-triggering tests and achieves 97% accuracy in detecting adversarial attacks. A video demonstration which shows the main features of DeepStellar is available at: https://sites.google.com/view/deepstellar/tool-demo.

Discipline

OS and Networks | Software Engineering

Research Areas

Software and Cyber-Physical Systems

Publication

Proceedings of the 34th IEEE/ACM International Conference on Automated Software Engineering, San Diego, 2019 November 11-15

First Page

1062

Last Page

1065

ISBN

9781728125084

Identifier

10.1109/ASE.2019.00102

Publisher

IEEE

City or Country

San Diego, California

Share

COinS