DeepStellar: model-based quantitative analysis of stateful Deep Learning systems

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

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

81 Citations (Scopus)


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).

Original languageEnglish
Title of host publicationESEC/FSE'19 - Proceedings of the 2019 27th ACM Joint Meeting European Software Engineering Conference and Symposium on the Foundations of Software Engineering
EditorsMarlon Dumas, Dietmar Pfahl, Sven Apel, Alessandra Russo
Place of PublicationNew York NY USA
PublisherAssociation for Computing Machinery (ACM)
Number of pages11
ISBN (Electronic)9781450355728
Publication statusPublished - 2019
Externally publishedYes
EventJoint Meeting of the European Software Engineering Conference and the ACM SIGSOFT Symposium on the Foundations of Software Engineering 2019 - Tallinn, Estonia
Duration: 26 Aug 201930 Aug 2019
Conference number: 27th


ConferenceJoint Meeting of the European Software Engineering Conference and the ACM SIGSOFT Symposium on the Foundations of Software Engineering 2019
Abbreviated titleESEC/FSE 2019
Internet address


  • Adversarial sample
  • Deep learning
  • Model-based analysis
  • Recurrent neural network
  • Testing

Cite this