Abstract
With the increasing application of neural networks in safety-critical domains, their robustness becomes a crucial concern. In this paper, we present a multi-neuron relaxation-based verification framework kProp for ReLU neural networks with adversarial distortions in general norms. In contrast with existing verification methods tackling general distortion norms, the proposed multi-neuron relaxation method is able to capture the relations among a group of neurons, thus providing tighter convex relaxations and improving verification precision. In addition, existing methods based on linear relaxation may include infeasible inputs to the neural network for robustness verification, which further leads to verification precision loss. To address this problem, we propose a region clipping method to exclude infeasible inputs to further improve the verification precision. We implement our verification framework and evaluate its performance on open-source benchmarks. The experiments show that kProp can produce precise verification results where existing verification methods fail to produce conclusive results, and can be applied to neural networks with more than 4k neurons in general distortion norms.
Current Address: Department of Computer Science, University of Oxford, Oxford, UK.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Amato, F., López, A., Peña-Méndez, E.M., Vaňhara, P., Hampl, A., Havel, J.: Artificial neural networks in medical diagnosis. J. Appl. Biomed. 11(2), 47–58 (2013)
Carlini, N., Wagner, D.: Towards evaluating the robustness of neural networks. In: 2017 IEEE Symposium on Security and Privacy (SP), pp. 39–57. IEEE (2017)
Chen, Z., Huang, X.: End-to-end learning for lane keeping of self-driving cars. In: 2017 IEEE Intelligent Vehicles Symposium (IV), pp. 1856–1860. IEEE (2017)
Ehlers, R.: Formal verification of piece-wise linear feed-forward neural networks. In: D’Souza, D., Narayan Kumar, K. (eds.) ATVA 2017. LNCS, vol. 10482, pp. 269–286. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-68167-2_19
Eykholt, K., et al.: Robust physical-world attacks on deep learning visual classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1625–1634 (2018)
Fukuda, K., Prodon, A.: Double description method revisited. In: Deza, M., Euler, R., Manoussakis, I. (eds.) CCS 1995. LNCS, vol. 1120, pp. 91–111. Springer, Heidelberg (1996). https://doi.org/10.1007/3-540-61576-8_77
Gagandeep, S., et al.: Eran verification dataset. https://github.com/eth-sri/eran
Gehr, T., Mirman, M., Drachsler-Cohen, D., Tsankov, P., Chaudhuri, S., Vechev, M.: AI2: safety and robustness certification of neural networks with abstract interpretation. In: 2018 IEEE Symposium on Security and Privacy (SP), pp. 3–18. IEEE (2018)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: 3rd International Conference on Learning Representations (ICLR), Conference Track Proceedings (2015)
Julian, K.D., Lopez, J., Brush, J.S., Owen, M.P., Kochenderfer, M.J.: Policy compression for aircraft collision avoidance systems. In: 2016 IEEE/AIAA 35th Digital Avionics Systems Conference (DASC), pp. 1–10. IEEE (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
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Lomuscio, A., Maganti, L.: An approach to reachability analysis for feed-forward ReLU neural networks (2017). https://arxiv.org/abs/1706.07351
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 Program. Lang. 6(POPL), 1–33 (2022)
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 (NeurIPS), vol. 32, pp. 15072–15083 (2019)
Singh, G., Gehr, T., Püschel, M., Vechev, M.: An abstract domain for certifying neural networks. Proc. ACM Program. Lang. 3(POPL), 1–30 (2019)
Wang, S., Pei, K., Whitehouse, J., Yang, J., Jana, S.: Efficient formal safety analysis of neural networks. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 31, pp. 6369–6379 (2018)
Wang, S., et al.: Beta-CROWN: efficient bound propagation with per-neuron split constraints for neural network robustness verification. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 34, pp. 29909–29921 (2021)
Weng, L., et al.: Towards fast computation of certified robustness for ReLU networks. In: Proceedings of the 35th International Conference on Machine Learning (ICML), vol. 80, pp. 5276–5285. PMLR (2018)
Zhang, H., Weng, T.W., Chen, P.Y., Hsieh, C.J., Daniel, L.: Efficient neural network robustness certification with general activation functions. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 31, pp. 4944–4953 (2018)
Acknowledgements
This research was sponsored by the National Natural Science Foundation of China under Grant No. 62172019, 61772038, 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
© 2023 IFIP International Federation for Information Processing
About this paper
Cite this paper
Xue, X., Zhang, X., Sun, M. (2023). kProp: Multi-neuron Relaxation Method for Neural Network Robustness Verification. In: Hojjat, H., Ábrahám, E. (eds) Fundamentals of Software Engineering. FSEN 2023. Lecture Notes in Computer Science, vol 14155 . Springer, Cham. https://doi.org/10.1007/978-3-031-42441-0_11
Download citation
DOI: https://doi.org/10.1007/978-3-031-42441-0_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-42440-3
Online ISBN: 978-3-031-42441-0
eBook Packages: Computer ScienceComputer Science (R0)