Abstract
The increasing prevalence of neural networks necessitates their verification in order to ensure security. Verifying neural networks is a challenge due to the use of non-linear activation functions. This work concentrates on approximating the convex hull of activation functions. An approach is proposed to construct a convex polytope to over-approximate the ReLU hull (the convex hull of the ReLU function) when considering multi-variables. The key idea is to construct new faces based on the known faces and vertices by uniqueness of the ReLU hull. Our approach has been incorporated into the state-of-the-art PRIMA framework, which takes into account multi-neuron constraints. The experimental evaluation demonstrates that our method is more efficient and precise than existing ReLU hull exact/approximate approaches, and it makes a significant contribution to the verification of neural networks. Our concept can be applied to other non-linear functions in neural networks, and this could be explored further in future research.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bunel, R., Turkaslan, I., Torr, P.H., Kohli, P., Kumar, M.P.: A unified view of piecewise linear neural network verification. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems, pp. 4795–4804 (2018)
Cao, Y., et al.: Invisible for both camera and lidar: security of multi-sensor fusion based perception in autonomous driving under physical-world attacks. In: 2021 IEEE Symposium on Security and Privacy (SP), pp. 176–194. IEEE (2021)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Katz, G., Barrett, C., Dill, D.L., Julian, K., Kochenderfer, M.J.: Reluplex: an efficient SMT solver for verifying deep neural networks. In: Majumdar, R., Kunčak, V. (eds.) CAV 2017. LNCS, vol. 10426, pp. 97–117. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-63387-9_5
Li, L., Xie, T., Li, B.: SoK: certified robustness for deep neural networks. In: 2023 IEEE Symposium on Security and Privacy (SP), pp. 94–115. IEEE Computer Society (2022)
Lomuscio, A., Maganti, L.: An approach to reachability analysis for feed-forward ReLU neural networks. arXiv preprint: arXiv:1706.07351 (2017)
Müller, M.N., Makarchuk, G., Singh, G., Püschel, M., Vechev, M.: PRIMA: general and precise neural network certification via scalable convex hull approximations. Proc. ACM Programm. Lang. 6(POPL), 1–33 (2022)
Pulina, L., Tacchella, A.: An abstraction-refinement approach to verification of artificial neural networks. In: Touili, T., Cook, B., Jackson, P. (eds.) CAV 2010. LNCS, vol. 6174, pp. 243–257. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-14295-6_24
Singh, G., Ganvir, R., Püschel, M., Vechev, M.: Beyond the single neuron convex barrier for neural network certification. In: Advances in Neural Information Processing Systems, vol. 32 (2019)
Singh, G., Gehr, T., Mirman, M., Püschel, M., Vechev, M.: Fast and effective robustness certification. In: Advances in Neural Information Processing Systems, vol. 31 (2018)
Singh, G., Gehr, T., Püschel, M., Vechev, M.: An abstract domain for certifying neural networks. Proce. ACM Programm. Lang. 3(POPL), 1–30 (2019)
Szegedy, C., et al.: Intriguing properties of neural networks. In: 2nd International Conference on Learning Representations, ICLR 2014 (2014)
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Weng, L., et al.: Towards fast computation of certified robustness for ReLU networks. In: International Conference on Machine Learning, pp. 5276–5285. PMLR (2018)
Zhang, H., et al.: General cutting planes for bound-propagation-based neural network verification. In: Advances in Neural Information Processing Systems, vol. 35, pp. 1656–1670 (2022)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Ma, Z. (2023). Verifying Neural Networks by Approximating Convex Hulls. In: Li, Y., Tahar, S. (eds) Formal Methods and Software Engineering. ICFEM 2023. Lecture Notes in Computer Science, vol 14308. Springer, Singapore. https://doi.org/10.1007/978-981-99-7584-6_17
Download citation
DOI: https://doi.org/10.1007/978-981-99-7584-6_17
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-7583-9
Online ISBN: 978-981-99-7584-6
eBook Packages: Computer ScienceComputer Science (R0)