DeepHunter: a coverage-guided fuzz testing framework for deep neural networks

Minhui Xue
Minhui Xue
Hongxu Chen
Hongxu Chen
Jianxiong Yin
Jianxiong Yin
Simon See
Simon See

Proceedings of the 28th ACM SIGSOFT International Symposium on Software Testing and Analysis, pp. 146-157, 2019.

Cited by: 68|Bibtex|Views48|Links
EI
Keywords:
Deep learning testing coverage-guided fuzzing metamorphic testing

Abstract:

The past decade has seen the great potential of applying deep neural network (DNN) based software to safety-critical scenarios, such as autonomous driving. Similar to traditional software, DNNs could exhibit incorrect behaviors, caused by hidden defects, leading to severe accidents and losses. In this paper, we propose DeepHunter, a cover...More

Code:

Data:

Your rating :
0

 

Tags
Comments