arrow
返回

Efficient and Effective Feature Space Exploration for Testing Deep Learning Systems

delete2023-03-29
delete25
delete
OA
AI
T
Tahereh Zohdinasab *
V
Vincenzo Riccio
A
Alessio Gambi
P
Paolo Tonella
DOI:10.1145/3544792delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Assessingthe quality of Deep Learning (DL) systems is crucial, as they are increasingly adopted in safetycritical domains. Researchers have proposed several input generation techniques for DL systems. While such techniques can expose failures, they do not explain which features of the test inputs influenced the system's (mis-) behaviour. DeepHyperion was the first test generator to overcome this limitation by exploring the DL systems' feature space at large. In this article, we propose DeepHyperion-CS, a test generator for DL systems that enhances DeepHyperion by promoting the inputs that contributed more to feature space exploration during the previous search iterations. We performed an empirical study involving two different test subjects (i.e., a digit classifier and a lane-keeping system for self-driving cars). Our results proved that the contribution-based guidance implemented within DeepHyperion-CS outperforms state-of-the-art tools and significantly improves the efficiency and the effectiveness of DeepHyperion. DeepHyperion-CS exposed significantly more misbehaviours for five out of six feature combinations and was up to 65% more efficient than DeepHyperion in finding misbehaviour-inducing inputs and exploring the feature space. DeepHyperion-CS was useful for expanding the datasets used to train the DL systems, populating up to 200% more feature map cells than the original training set.
Keyword:
Software testing
Deep Learning
search based software engineering
self-driving cars

期刊

A
ACM Transactions on Software Engineering and Methodology
IF:
6.2
论文数:
1.2K
被引数:
3.4K

机构

U
Universita della Svizzera Italiana
学者数:
3.3K
论文数: 2.8K
被引数: 3
U
University of Passau
学者数:
692
论文数: 680
被引数: 515
引用论文

引用论文

Testing machine learning based systems: a systematic mapping测试基于机器学习的系统: 系统映射
err2020-09-15
err145
errOAAI
errRiccio, Vincenzo; Jahangirova, Gunel; Stocco, Andrea; Humbatova, Nargiz; Weiss, Michael; Tonella, Paolo
err分享
err收藏
Mutation in the Mismatch Repair Gene Msh6 Causes Cancer Susceptibility
errCell
IF0
err1997-11-01
err0
errOAAI
errWinfried Edelmann; Kan Yang; Asad Umar; Joerg Heyer; Kirkland Lau; Kunhua Fan; Wolfgang Liedtke; Paula E Cohen; Michael F Kane; James R Lipford; Nianjun Yu; Gray F Crouse; Jeffrey W Pollard; Thomas Kunkel; Martin Lipkin; Richard Kolodner; Raju Kucherlapati
err分享
err收藏
学者 查看更多内容