Coverage-Guided Fuzzing for FeedForward Neural Networks

Xiaofei Xie, Hongxu Chen, Yi Li, Lei Ma, Yang Liu, and Jianjun Zhao

In Proceedings of the 34th IEEE/ACM International Conference on Automated Software Engineering (ASE), 2019

Abstract: Deep neural network (DNN) has been widely applied to safety-critical scenarios such as autonomous vehicle, security surveillance, and cyber-physical control systems. Yet, the incorrect behaviors of DNNs can lead to severe accidents and tremendous losses due to hidden defects. In this paper, we present DeepHunter, a general-purpose fuzzing framework for detecting defects of DNNs. DeepHunter is inspired by traditional grey-box fuzzing and aims to increase the overall test coverage by applying adaptive heuristics according to runtime feedback. Specifically, DeepHunter provides a series of seed selection strategies, metamorphic mutation strategies, and testing criteria customized to DNN testing; all these components support multiple built-in configurations which are easy to extend. We evaluated DeepHunter on two popular datasets and the results demonstrate the effectiveness of DeepHunter in achieving coverage increase and detecting real defects. A video demonstration which showcases the main features of DeepHunter can be found at https://youtu.be/s5DfLErcgrc.

Cite:

@inproceedings{Xie2019CGF,
  author = {Xie, Xiaofei and Chen, Hongxu and Li, Yi and Ma, Lei and Liu, Yang and Zhao, Jianjun},
  booktitle = {Proceedings of the 34th IEEE/ACM International Conference on Automated Software Engineering (ASE)},
  month = nov,
  pages = {1162--1165},
  title = {Coverage-Guided Fuzzing for FeedForward Neural Networks},
  year = {2019}
}