Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
11-2019
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.
Discipline
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
1162
Last Page
1165
ISBN
9781728125084
Identifier
10.1109/ASE.2019.00127
Publisher
IEEE Press
City or Country
San Diego, California
Citation
XIE, Xiaofei; CHEN, Hongxu; LI, Yi; MA, Lei; LIU, Yang; and ZHAO, Jianjun.
Coverage-guided fuzzing for feedforward neural networks. (2019). Proceedings of the 34th IEEE/ACM International Conference on Automated Software Engineering, San Diego, 2019 November 11-15. 1162-1165.
Available at: https://ink.library.smu.edu.sg/sis_research/7067
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.