TY - GEN
T1 - Coverage-guided fuzzing for feedforward neural networks
AU - Xie, Xiaofei
AU - Chen, Hongxu
AU - Li, Yi
AU - Ma, Lei
AU - Liu, Yang
AU - Zhao, Jianjun
PY - 2019/11
Y1 - 2019/11
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85078883804&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85078883804&partnerID=8YFLogxK
U2 - 10.1109/ASE.2019.00127
DO - 10.1109/ASE.2019.00127
M3 - Conference contribution
T3 - Proceedings - 2019 34th IEEE/ACM International Conference on Automated Software Engineering, ASE 2019
SP - 1162
EP - 1165
BT - Proceedings - 2019 34th IEEE/ACM International Conference on Automated Software Engineering, ASE 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 34th IEEE/ACM International Conference on Automated Software Engineering, ASE 2019
Y2 - 10 November 2019 through 15 November 2019
ER -