Deephunter: A coverage-guided fuzz testing framework for deep neural networks

Xiaofei Xie, Lei Ma, Felix Juefei-Xu, Minhui Xue, Hongxu Chen, Yang Liu, Jianjun Zhao, Bo Li, Jianxiong Yin, Simon See

研究成果: Chapter in Book/Report/Conference proceedingConference contribution

82 被引用数 (Scopus)

抄録

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 coverage-guided fuzz testing framework for detecting potential defects of general-purpose DNNs. To this end, we first propose a metamorphic mutation strategy to generate new semantically preserved tests, and leverage multiple extensible coverage criteria as feedback to guide the test generation. We further propose a seed selection strategy that combines both diversity-based and recency-based seed selection. We implement and incorporate 5 existing testing criteria and 4 seed selection strategies in DeepHunter. Large-scale experiments demonstrate that (1) our metamorphic mutation strategy is useful to generate new valid tests with the same semantics as the original seed, by up to a 98% validity ratio; (2) the diversity-based seed selection generally weighs more than recency-based seed selection in boosting the coverage and in detecting defects; (3) DeepHunter outperforms the state of the arts by coverage as well as the quantity and diversity of defects identified; (4) guided by corner-region based criteria, DeepHunter is useful to capture defects during the DNN quantization for platform migration.

本文言語英語
ホスト出版物のタイトルISSTA 2019 - Proceedings of the 28th ACM SIGSOFT International Symposium on Software Testing and Analysis
編集者Dongmei Zhang, Anders Moller
出版社Association for Computing Machinery, Inc
ページ158-168
ページ数11
ISBN(電子版)9781450362245
DOI
出版ステータス出版済み - 7 10 2019
イベント28th ACM SIGSOFT International Symposium on Software Testing and Analysis, ISSTA 2019 - Beijing, 中国
継続期間: 7 15 20197 19 2019

出版物シリーズ

名前ISSTA 2019 - Proceedings of the 28th ACM SIGSOFT International Symposium on Software Testing and Analysis

会議

会議28th ACM SIGSOFT International Symposium on Software Testing and Analysis, ISSTA 2019
国/地域中国
CityBeijing
Period7/15/197/19/19

All Science Journal Classification (ASJC) codes

  • 計算理論と計算数学
  • コンピュータ サイエンスの応用
  • ソフトウェア

フィンガープリント

「Deephunter: A coverage-guided fuzz testing framework for deep neural networks」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル