Models of Computational Profiles to Study the Likelihood of DNN Metamorphic Test Cases
Abstract
Neural network test cases are meant to exercise different reasoning paths in an architecture and used to validate the prediction outcomes. In this paper, we introduce "computational profiles" as vectors of neuron activation levels. We investigate the distribution of computational profile likelihood of metamorphic test cases with respect to the likelihood distributions of training, test and error control cases. We estimate the nonparametric probability densities of neuron activation levels for each distinct output class. Probabilities are inferred using training cases only, without any additional knowledge about metamorphic test cases. Experiments are performed by training a network on the MNIST Fashion library of images and comparing prediction likelihoods with those obtained from error controldata and from metamorphic test cases. Experimental results show that the distributions of computational profile likelihood for training and test cases are somehow similar, while the distribution of the randomnoise controldata is always remarkably lower than the observed one for the training and testing sets. In contrast, metamorphic test cases show a prediction likelihood that lies in an extended range with respect to training, tests, and random noise. Moreover, the presented approach allows the independent assessment of different training classes and experiments to show that some of the classes are more sensitive to misclassifying metamorphic test cases than other classes. In conclusion, metamorphic test cases represent very aggressive tests for neural network architectures. Furthermore, since metamorphic test cases force a network to misclassify those inputs whose likelihood is similar to that of training cases, they could also be considered as adversarial attacks that evade defenses based on computational profile likelihood evaluation.
 Publication:

arXiv eprints
 Pub Date:
 July 2021
 DOI:
 10.48550/arXiv.2107.13491
 arXiv:
 arXiv:2107.13491
 Bibcode:
 2021arXiv210713491M
 Keywords:

 Computer Science  Machine Learning;
 Computer Science  Software Engineering
 EPrint:
 9 pages (10 pages with ref.)