Variable Strength Combinatorial Testing for Deep Neural Networks

In deep neural networks (DNNs), each neuron in the post-layer receives the influence of all the neurons in the pre-layer. As we known, different connections in a DNN model have different weights. It means that, different combinations of pre-layer neurons have different effects on the post-layer neurons. Therefore, the variable strength combinatorial testing can reflect the effect of combination interaction of neurons in the pre-layer on the neurons in the post-layer. In this paper, we propose to adopt variable strength combinatorial testing technique on DNNs testing. In order to modeling the effect of combinatorial interaction of pre-layer neurons on the post-layer neurons, we propose three methods to construct variable strength combinatorial interaction relationship for DNNs. The experimental results show that, 1) variable strength combinatorial coverage criteria are discriminating to measure the adequacy of DNNs testing, and 2) there is correlation between variable strength combinatorial coverage and adversarial detection.

[1]  Junfeng Yang,et al.  DeepXplore: Automated Whitebox Testing of Deep Learning Systems , 2017, SOSP.

[2]  Ajmal Mian,et al.  Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey , 2018, IEEE Access.

[3]  Lei Ma,et al.  DeepCT: Tomographic Combinatorial Testing for Deep Learning Systems , 2019, 2019 IEEE 26th International Conference on Software Analysis, Evolution and Reengineering (SANER).

[4]  Ian Goodfellow,et al.  TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing , 2018, ICML.

[5]  Myra B. Cohen,et al.  A variable strength interaction testing of components , 2003, Proceedings 27th Annual International Computer Software and Applications Conference. COMPAC 2003.

[6]  Huichen Lihuichen DECISION-BASED ADVERSARIAL ATTACKS: RELIABLE ATTACKS AGAINST BLACK-BOX MACHINE LEARNING MODELS , 2017 .

[7]  Yadong Wang,et al.  Combinatorial Testing for Deep Learning Systems , 2018, ArXiv.

[8]  Ananthram Swami,et al.  The Limitations of Deep Learning in Adversarial Settings , 2015, 2016 IEEE European Symposium on Security and Privacy (EuroS&P).

[9]  Baowen Xu,et al.  Greedy Heuristic Algorithms to Generate Variable Strength Combinatorial Test Suite , 2008, 2008 The Eighth International Conference on Quality Software.

[10]  Lei Ma,et al.  DeepGauge: Multi-Granularity Testing Criteria for Deep Learning Systems , 2018, 2018 33rd IEEE/ACM International Conference on Automated Software Engineering (ASE).

[11]  Hareton K. N. Leung,et al.  A survey of combinatorial testing , 2011, CSUR.

[12]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.