Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

9-2020

Abstract

Neural networks are becoming a popular tool for solving many realworld problems such as object recognition and machine translation, thanks to its exceptional performance as an end-to-end solution. However, neural networks are complex black-box models, which hinders humans from interpreting and consequently trusting them in making critical decisions. Towards interpreting neural networks, several approaches have been proposed to extract simple deterministic models from neural networks. The results are not encouraging (e.g., low accuracy and limited scalability), fundamentally due to the limited expressiveness of such simple models.In this work, we propose an approach to extract probabilistic automata for interpreting an important class of neural networks, i.e., recurrent neural networks. Our work distinguishes itself from existing approaches in two important ways. One is that probability is used to compensate for the loss of expressiveness. This is inspired by the observation that human reasoning is often 'probabilistic'. The other is that we adaptively identify the right level of abstraction so that a simple model is extracted in a request-specific way. We conduct experiments on several real-world datasets using state-of-the-art architectures including GRU and LSTM. The result shows that our approach significantly improves existing approaches in terms of accuracy or scalability. Lastly, we demonstrate the usefulness of the extracted models through detecting adversarial texts.

Keywords

Abstraction, Interpretation, Probabilistic automata, Recurrent neural networks

Discipline

Software Engineering

Research Areas

Software and Cyber-Physical Systems

Publication

2020 35th IEEE/ACM International Conference on Automated Software Engineering ASE: Virtual, September 21-25: Proceedings

First Page

499

Last Page

510

ISBN

9781450367684

Identifier

10.1145/3324884.3416592

Publisher

ACM

City or Country

New York

Embargo Period

5-17-2021

Copyright Owner and License

Authors

Additional URL

https://doi.org/10.1145/3324884.3416592

Share

COinS