Abstract
Deep learning (DL) systems have achieved significant success in numerous cutting-edge fields. However, the deployment of DL systems in safety-critical areas has raised public concerns about their correctness and robustness. To provide testing evidence for the dependable behavior of Deep Neural Networks (DNNs), various DL coverage criteria have been proposed. These coverage criteria are often “ad-hoc” in terms of granularity for different tasks, but designing appropriate criteria for every possible usage scenario is infeasible and will make the coverage testing lack of uniform standards. In this paper, we proposes a variable-grained DL coverage criterion named HeatC as a common solution for different coverage testing tasks. HeatC leverages class-activation-map-based features from neural networks and clusters these features to generate test targets. Experiments demonstrate that HeatC outperforms existing mainstream coverage criteria in assessing the adequacy of test suites and selecting high-value test samples from unlabeled datasets.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chattopadhay, A., Sarkar, A., Howlader, P., Balasubramanian, V.N.: Grad-CAM++: generalized gradient-based visual explanations for deep convolutional networks. In: Proceedings of the 18th IEEE Winter Conference on Applications of Computer Vision, pp. 839–847. IEEE Computer Society (2018). https://doi.org/10.1109/WACV.2018.00097
Chen, J., Song, L., Wainwright, M.J., Jordan, M.I.: Learning to explain: an information-theoretic perspective on model interpretation. In: Proceedings of the 35th International Conference on Machine Learning, ICML 2018, pp. 1386–1418. PMLR 80. International Machine Learning Society (2018). https://doi.org/10.48550/arXiv.1802.07814
Desai, S., Ramaswamy, H.G.: Ablation-CAM: visual explanations for deep convolutional network via gradient-free localization. In: Proceedings of the 2020 IEEE Winter Conference on Applications of Computer Vision, pp. 972–980. IEEE (2020). https://doi.org/10.1109/WACV45572.2020.9093360
Dhillon, G.S., et al.: Stochastic activation pruning for robust adversarial defense. In: Proceedings of the 6th International Conference on Learning Representations. International Conference on Learning Representations (2018). https://doi.org/10.48550/arXiv.1803.01442
Feng, D., Harakeh, A., Waslander, S.L., Dietmayer, K.: A review and comparative study on probabilistic object detection in autonomous driving. IEEE Trans. Intell. Transp. Syst. 23(8), 9961–9980 (2022). https://doi.org/10.1109/TITS.2021.3096854
Gehr, T., Mirman, M., Drachsler-Cohen, D., Tsankov, P., Chaudhuri, S., Vechev, M.T.: AI2: safety and robustness certification of neural networks with abstract interpretation. In: Proceedings of the 2018 IEEE Symposium on Security and Privacy, pp. 3–18. IEEE Computer Society (2018). https://doi.org/10.1109/SP.2018.00058
Gerasimou, S., Eniser, H.F., Sen, A., Cakan, A.: Importance-driven deep learning system testing. In: Proceedings of the 42nd International Conference on Software Engineering: Companion, pp. 322–323. IEEE (2020). https://doi.org/10.1145/3377812.3390793
Gerges, F., Boufadel, M.C., Bou-Zeid, E., Nassif, H., Wang, J.T.L.: A novel deep learning approach to the statistical downscaling of temperatures for monitoring climate change. In: Proceedings of the 6th International Conference on Machine Learning and Soft Computing, pp. 1–7. Advances in Intelligent Systems and Computing 887, ACM, Virtual, Online, China (2022)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: Proceedings of the 3rd International Conference on Learning Representations. International Conference on Learning Representations (2015). http://arxiv.org/abs/1412.6572
Guller, D.: Technical foundations of a DPLL-based SAT solver for propositional Godel logic. IEEE Trans. Fuzzy Syst. 26(1), 84–100 (2018). https://doi.org/10.1109/TFUZZ.2016.2637374
Kim, J., Feldt, R., Yoo, S.: Guiding deep learning system testing using surprise adequacy. In: Proceedings of the 41st International Conference on Software Engineering, pp. 1039–1049. IEEE (2019). https://doi.org/10.1109/ICSE.2019.00108
Kim, S., Wimmer, H., Kim, J.: Analysis of deep learning libraries: Keras, Pytorch, and MXnet. In: Proceedings of the 20th IEEE/ACIS International Conference on Software Engineering Research, Management and Applications, pp. 54–62. IEEE (2022). https://doi.org/10.1109/SERA54885.2022.9806734
Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. Technical report, pp. 32–33 (2009). https://www.cs.toronto.edu/kriz/learning-features-2009-TR.pdf
Kurakin, A., Goodfellow, I.J., Bengio, S.: Adversarial examples in the physical world. In: Proceedings of the 5th International Conference on Learning Representations. International Conference on Learning Representations (2019). https://openreview.net/forum?id=HJGU3Rodl
Lin, M., Chen, Q., Yan, S.: Network in network. In: Proceedings of the 2nd International Conference on Learning Representations. International Conference on Learning Representations (2014)
Ma, L., et al.: DeepCT: tomographic combinatorial testing for deep learning systems. In: Proceedings of the 26th IEEE International Conference on Software Analysis, Evolution and Reengineering, pp. 614–618. IEEE (2019). https://doi.org/10.1109/SANER.2019.8668044
Ma, L., et al.: DeepGauge: multi-granularity testing criteria for deep learning systems. In: Proceedings of the 33rd ACM/IEEE International Conference on Automated Software Engineering, pp. 120–131. ACM (2018). https://doi.org/10.1145/3238147.3238202
Mahendran, A., Vedaldi, A.: Understanding deep image representations by inverting them, pp. 5188–5196. IEEE Computer Society (2015). https://doi.org/10.1109/CVPR.2015.7299155
Omeiza, D., Speakman, S., Cintas, C., Weldemariam, K.: Smooth grad-CAM++: an enhanced inference level visualization technique for deep convolutional neural network models. CoRR abs/1908.01224 (2019). http://arxiv.org/abs/1908.01224
Pei, K., Cao, Y., Yang, J., Jana, S.: Towards practical verification of machine learning: the case of computer vision systems. CoRR abs/1712.01785 (2017). http://arxiv.org/abs/1712.01785
Pei, K., Cao, Y., Yang, J., Jana, S.: DeepXplore: automated whitebox testing of deep learning systems. In: Proceedings of the 26th ACM Symposium on Operating Systems Principles, pp. 1–18. ACM (2018). https://doi.org/10.1145/3132747.3132785
Poursaeed, O., Katsman, I., Gao, B., Belongie, S.: Generative adversarial perturbations, pp. 4422–4431. IEEE Computer Society (2018). https://doi.org/10.1109/CVPR.2018.00465
Razumovskaia, E., Glavas, G., Majewska, O., Ponti, E.M., Vulic, I.: Natural language processing for multilingual task-oriented dialogue. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, pp. 44–50. Association for Computational Linguistics (2022). https://doi.org/10.18653/v1/2022.acl-tutorials.8
Salay, R., Czarnecki, K.: Using machine learning safely in automotive software: an assessment and adaption of software process requirements in ISO 26262. CoRR abs/1808.01614 (2018). http://arxiv.org/abs/1808.01614
Sekhon, J., Fleming, C.: Towards improved testing for deep learning. In: Proceedings of the 41st International Conference on Software Engineering, pp. 85–88. IEEE (2019). https://doi.org/10.1109/ICSE-NIER.2019.00030
Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. Int. J. Comput. Vis. 128(2), 336–359 (2020). https://doi.org/10.1007/s11263-019-01228-7
Sun, W., Lu, Y., Sun, M.: Are coverage criteria meaningful metrics for DNNs? In: Proceedings of the 2021 International Joint Conference on Neural Networks, pp. 1–8. IEEE (2021). https://doi.org/10.1109/IJCNN52387.2021.9533987
Sun, Y., Huang, X., Kroening, D.: Testing deep neural networks. CoRR abs/1803.04792 (2018). http://arxiv.org/abs/1803.04792
Udeshi, S., Arora, P., Chattopadhyay, S.: Automated directed fairness testing. In: Proceedings of the 33rd ACM/IEEE International Conference on Automated Software Engineering, pp. 98–108. ACM (2018). https://doi.org/10.1145/3238147.3238165
Wang, H., et al.: Score-CAM: score-weighted visual explanations for convolutional neural networks. In: Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 111–119. IEEE (2020). https://doi.org/10.1109/CVPRW50498.2020.00020
Xiao, H., Rasul, K., Vollgraf, R.: Fashion MNIST: an MNIST-like dataset of 70,000 \(28 \times 28\) labeled fashion images (2017). https://github.com/zalandoresearch/fashion-mnist
Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the 31st IEEE Conference on Computer Vision and Pattern Recognition, pp. 586–595. IEEE Computer Society (2018). https://doi.org/10.1109/CVPR.2018.00068
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: Proceedings of the 29th IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921–2929. IEEE Computer Society (2016). https://doi.org/10.1109/CVPR.2016.319
Acknowledgement
This research was sponsored by the National Natural Science Foundation of China under Grant No. 62172019, and CCF-Huawei Formal Verification Innovation Research Plan.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Sun, W., Lu, Y., Luan, X., Sun, M. (2024). HeatC: A Variable-Grained Coverage Criterion for Deep Learning Systems. In: Hermanns, H., Sun, J., Bu, L. (eds) Dependable Software Engineering. Theories, Tools, and Applications. SETTA 2023. Lecture Notes in Computer Science, vol 14464. Springer, Singapore. https://doi.org/10.1007/978-981-99-8664-4_14
Download citation
DOI: https://doi.org/10.1007/978-981-99-8664-4_14
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8663-7
Online ISBN: 978-981-99-8664-4
eBook Packages: Computer ScienceComputer Science (R0)