DeepStellar: Model-based quantitative analysis of stateful deep learning systems

Xiaoning Du, Xiaofei Xie, Yi Li, Lei Ma, Yang Liu, Jianjun Zhao

研究成果: Chapter in Book/Report/Conference proceedingConference contribution

48 被引用数 (Scopus)

抄録

Deep Learning (DL) has achieved tremendous success in many cutting-edge applications. However, the state-of-the-art DL systems still suffer from quality issues. While some recent progress has been made on the analysis of feed-forward DL systems, little study has been done on the Recurrent Neural Network (RNN)-based stateful DL systems, which are widely used in audio, natural languages and video processing, etc. In this paper, we initiate the very first step towards the quantitative analysis of RNN-based DL systems. We model RNN as an abstract state transition system to characterize its internal behaviors. Based on the abstract model, we design two trace similarity metrics and five coverage criteria which enable the quantitative analysis of RNNs. We further propose two algorithms powered by the quantitative measures for adversarial sample detection and coverage-guided test generation. We evaluate DeepStellar on four RNN-based systems covering image classification and automated speech recognition. The results demonstrate that the abstract model is useful in capturing the internal behaviors of RNNs, and confirm that (1) the similarity metrics could effectively capture the differences between samples even with very small perturbations (achieving 97% accuracy for detecting adversarial samples) and (2) the coverage criteria are useful in revealing erroneous behaviors (generating three times more adversarial samples than random testing and hundreds times more than the unrolling approach).

本文言語英語
ホスト出版物のタイトルESEC/FSE 2019 - Proceedings of the 2019 27th ACM Joint Meeting European Software Engineering Conference and Symposium on the Foundations of Software Engineering
編集者Sven Apel, Marlon Dumas, Alessandra Russo, Dietmar Pfahl
出版社Association for Computing Machinery, Inc
ページ477-487
ページ数11
ISBN(電子版)9781450355728
DOI
出版ステータス出版済み - 8 12 2019
イベント27th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, ESEC/FSE 2019 - Tallinn, エストニア
継続期間: 8 26 20198 30 2019

出版物シリーズ

名前ESEC/FSE 2019 - Proceedings of the 2019 27th ACM Joint Meeting European Software Engineering Conference and Symposium on the Foundations of Software Engineering

会議

会議27th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, ESEC/FSE 2019
国/地域エストニア
CityTallinn
Period8/26/198/30/19

All Science Journal Classification (ASJC) codes

  • 人工知能
  • ソフトウェア

フィンガープリント

「DeepStellar: Model-based quantitative analysis of stateful deep learning systems」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル