Abstract
With the expanding role of neural networks, the need for complete and sound verification of their property has become critical. In the recent years, it was established that Binary Neural Networks (BNNs) have an equivalent representation in Boolean logic and can be formally analyzed using logical reasoning tools such as SAT solvers. However, to date, only BNNs can be transformed into a SAT formula. In this work, we introduce Truth Table Deep Convolutional Neural Networks (TTnets), a new family of SAT-encodable models featuring for the first time real-valued weights. Furthermore, it admits, by construction, some valuable conversion features including post-tuning and tractability in the robustness verification setting. The latter property leads to a more compact SAT symbolic encoding than BNNs. This enables the use of general SAT solvers, making property verification easier. We demonstrate the value of TTnets regarding the formal robustness property: TTnets outperform the verified accuracy of all BNNs with a comparable computation time. More generally, they represent a relevant trade-off between all known complete verification methods: TTnets achieve high verified accuracy with fast verification time, being complete with no timeouts. We are exploring here a proof of concept of TTnets for a very important application (complete verification of robustness) and we believe this novel real-valued network constitutes a practical response to the rising need for functional formal verification. We postulate that TTnets can apply to various CNN-based architectures and be extended to other properties such as fairness, fault attack and exact rule extraction.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Andriushchenko, M., Hein, M.: Provably robust boosted decision stumps and trees against adversarial attacks. In: Advances in Neural Information Processing Systems, vol. 32 (2019)
Araujo, A., Norris, W., Sim, J.: Computing receptive fields of convolutional neural networks. Distill (2019). https://doi.org/10.23915/distill.00021, https://distill.pub/2019/computing-receptive-fields
Baluta, T., Shen, S., Shinde, S., Meel, K.S., Saxena, P.: Quantitative verification of neural networks and its security applications. In: Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security, pp. 1249–1264 (2019)
Bello, I., et al.: Revisiting resnets: Improved training and scaling strategies. arXiv preprint arXiv:2103.07579 (2021)
Biere, A., Heule, M., van Maaren, H.: Handbook of satisfiability, vol. 185. IOS press (2009)
Brown, T.B., et al.: Language models are few-shot learners. arXiv preprint arXiv:2005.14165 (2020)
Carlini, N., Katz, G., Barrett, C., Dill, D.L.: Provably minimally-distorted adversarial examples. arXiv preprint arXiv:1709.10207 (2017)
Chabanne, H., De Wargny, A., Milgram, J., Morel, C., Prouff, E.: Privacy-preserving classification on deep neural network. Cryptology ePrint Archive (2017)
Cheng, C.-H., Nührenberg, G., Huang, C.-H., Ruess, H.: Verification of binarized neural networks via inter-neuron factoring. In: Piskac, R., Rümmer, P. (eds.) VSTTE 2018. LNCS, vol. 11294, pp. 279–290. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-03592-1_16
Cheng, C.-H., Nührenberg, G., Ruess, H.: Maximum resilience of artificial neural networks. In: D’Souza, D., Narayan Kumar, K. (eds.) ATVA 2017. LNCS, vol. 10482, pp. 251–268. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-68167-2_18
De Palma, A., Bunel, R., Dvijotham, K., Kumar, M.P., Stanforth, R.: IBP regularization for verified adversarial robustness via branch-and-bound. arXiv preprint arXiv:2206.14772 (2022)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR09 (2009)
Dosovitskiy, A., et al.: An image is worth 16 \(\times \) 16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)
Driscoll, M.: System and method for adapting a neural network model on a hardware platform, 2 July 2020, US Patent App. 16/728,884
Dumoulin, V., Visin, F.: A guide to convolution arithmetic for deep learning. arXiv preprint arXiv:1603.07285 (2016)
Dvijotham, K., et al.: Training verified learners with learned verifiers. arXiv preprint arXiv:1805.10265 (2018)
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
Ferrari, C., Muller, M.N., Jovanovic, N., Vechev, M.: Complete verification via multi-neuron relaxation guided branch-and-bound. arXiv preprint arXiv:2205.00263 (2022)
Garg, S., Perot, V., Limtiaco, N., Taly, A., Chi, E.H., Beutel, A.: Counterfactual fairness in text classification through robustness. In: Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society, pp. 219–226 (2019)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press (2016). http://www.deeplearningbook.org
Hong, S., Frigo, P., Kaya, Y., Giuffrida, C., Dumitras, T.: Terminal brain damage: exposing the graceless degradation in deep neural networks under hardware fault attacks. In: 28th USENIX Security Symposium (USENIX Security 19), pp. 497–514 (2019)
Huan, Z., Kaidi, X., Shiqi, W., Cho-Jui, H.: Aaai 2022: ‘tutorial on neural network verification: Theory and practice’ (2022). https://neural-network-verification.com/
Hubara, I., Courbariaux, M., Soudry, D., El-Yaniv, R., Bengio, Y.: Binarized neural networks. In: Advances in Neural Information Processing Systems, vol. 29 (2016)
Jia, K., Rinard, M.: Efficient exact verification of binarized neural networks. arXiv preprint arXiv:2005.03597 (2020)
Jia, K., Rinard, M.: Exploiting verified neural networks via floating point numerical error. In: Drăgoi, C., Mukherjee, S., Namjoshi, K. (eds.) SAS 2021. LNCS, vol. 12913, pp. 191–205. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-88806-0_9
Jia, K., Rinard, M.: Verifying low-dimensional input neural networks via input quantization. In: Drăgoi, C., Mukherjee, S., Namjoshi, K. (eds.) SAS 2021. LNCS, vol. 12913, pp. 206–214. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-88806-0_10
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
Kurtz, J., Bah, B.: Efficient and robust mixed-integer optimization methods for training binarized deep neural networks. arXiv preprint arXiv:2110.11382 (2021)
Liffiton, M.H., Maglalang, J.C.: A cardinality solver: more expressive constraints for free. In: Cimatti, A., Sebastiani, R. (eds.) SAT 2012. LNCS, vol. 7317, pp. 485–486. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-31612-8_47
Liu, Z., Wu, B., Luo, W., Yang, X., Liu, W., Cheng, K.-T.: Bi-Real Net: enhancing the performance of 1-Bit cnns with improved representational capability and advanced training algorithm. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 747–763. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01267-0_44
Lomuscio, A., Maganti, L.: An approach to reachability analysis for feed-forward Relu neural networks. arXiv preprint arXiv:1706.07351 (2017)
Lomuscio, A., Qu, H., Raimondi, F.: MCMAS: an open-source model checker for the verification of multi-agent systems. Int. J. Softw. Tools Technol. Transfer 19(1), 9–30 (2017)
Mirman, M., Gehr, T., Vechev, M.: Differentiable abstract interpretation for provably robust neural networks. In: International Conference on Machine Learning, pp. 3578–3586. PMLR (2018)
Müller, M.N., Makarchuk, G., Singh, G., Püschel, M., Vechev, M.: Prima: general and precise neural network certification via scalable convex hull approximations. In: Proceedings of the ACM on Programming Languages 6(POPL), pp. 1–33 (2022)
Narodytska, N., Kasiviswanathan, S., Ryzhyk, L., Sagiv, M., Walsh, T.: Verifying properties of binarized deep neural networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)
Narodytska, N., Shrotri, A., Meel, K.S., Ignatiev, A., Marques-Silva, J.: Assessing heuristic machine learning explanations with model counting. In: Janota, M., Lynce, I. (eds.) SAT 2019. LNCS, vol. 11628, pp. 267–278. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-24258-9_19
Narodytska, N., Zhang, H., Gupta, A., Walsh, T.: In search for a sat-friendly binarized neural network architecture. In: International Conference on Learning Representations (2019)
Quine, W.V.: The problem of simplifying truth functions. Am. Math. Mon. 59(8), 521–531 (1952)
Raghunathan, A., Steinhardt, J., Liang, P.: Certified defenses against adversarial examples. arXiv preprint arXiv:1801.09344 (2018)
Rakin, A.S., He, Z., Fan, D.: Tbt: Targeted neural network attack with bit trojan. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 13198–13207 (2020)
Rastegari, M., Ordonez, V., Redmon, J., Farhadi, A.: XNOR-Net: Imagenet classification using binary convolutional neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 525–542. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_32
Regulation, G.D.P.: Regulation eu 2016/679 of the european parliament and of the council of 27 April 2016. Official Journal of the European Union (2016). http://ec.europa.eu/justice/data-protection/reform/files/regulation_oj_en.pdf. Accessed 20 Sept 2017
Roussel, O., Manquinho, V.: Pseudo-Boolean and cardinality constraints. In: Handbook of Satisfiability, pp. 695–733. IOS Press (2009)
Sahoo, S.S., Venugopalan, S., Li, L., Singh, R., Riley, P.: Scaling symbolic methods using gradients for neural model explanation. arXiv preprint arXiv:2006.16322 (2020)
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv 2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510–4520 (2018)
Sanyal, A., Kusner, M., Gascon, A., Kanade, V.: Tapas: tricks to accelerate (encrypted) prediction as a service. In: International Conference on Machine Learning, pp. 4490–4499. PMLR (2018)
Shih, A., Darwiche, A., Choi, A.: Verifying binarized neural networks by local automaton learning. In: AAAI Spring Symposium on Verification of Neural Networks (VNN) (2019)
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., Püschel, M., Vechev, M.: An abstract domain for certifying neural networks. In: Proceedings of the ACM on Programming Languages 3(POPL), pp. 1–30 (2019)
Sun, B., Sun, J., Dai, T., Zhang, L.: Probabilistic verification of neural networks against group fairness. In: Huisman, M., Păsăreanu, C., Zhan, N. (eds.) FM 2021. LNCS, vol. 13047, pp. 83–102. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-90870-6_5
Tjeng, V., Xiao, K., Tedrake, R.: Evaluating robustness of neural networks with mixed integer programming. In: ICLR (2019)
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998–6008 (2017)
Wang, S., et al.: Beta-crown: Efficient bound propagation with per-neuron split constraints for complete and incomplete neural network verification. arXiv preprint arXiv:2103.06624 (2021)
Wang, Z., Zhang, W., Liu, N., Wang, J.: Scalable rule-based representation learning for interpretable classification. In: Advances in Neural Information Processing Systems, vol. 34 (2021)
Wong, E., Kolter, Z.: Provable defenses against adversarial examples via the convex outer adversarial polytope. In: International Conference on Machine Learning, pp. 5286–5295. PMLR (2018)
Wong, E., Schmidt, F.R., Metzen, J.H., Kolter, J.Z.: Scaling provable adversarial defenses. arXiv preprint arXiv:1805.12514 (2018)
Wu, H., Barrett, C., Sharif, M., Narodytska, N., Singh, G.: Scalable verification of GNN-based job schedulers. arXiv preprint arXiv:2203.03153 (2022)
Xiao, K.Y., Tjeng, V., Shafiullah, N.M.M., Madry, A.: Training for faster adversarial robustness verification via inducing Relu stability. In: International Conference on Learning Representations (2019)
Xu, K., et al.: Automatic perturbation analysis for scalable certified robustness and beyond. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol. 33, pp. 1129–1141. Curran Associates, Inc. (2020). https://proceedings.neurips.cc/paper/2020/file/0cbc5671ae26f67871cb914d81ef8fc1-Paper.pdf
Yang, F., et al.: Learning interpretable decision rule sets: a submodular optimization approach. In: Advances in Neural Information Processing Systems, vol. 34 (2021)
Zhang, B., Cai, T., Lu, Z., He, D., Wang, L.: Towards certifying l-infinity robustness using neural networks with l-INF-DIST neurons. In: International Conference on Machine Learning, pp. 12368–12379. PMLR (2021)
Zhang, H., et al.: Towards stable and efficient training of verifiably robust neural networks. arXiv preprint arXiv:1906.06316 (2019)
Zhang, Y., Zhao, Z., Chen, G., Song, F., Chen, T.: BDD4BNN: a BDD-based quantitative analysis framework for binarized neural networks. In: Silva, A., Leino, K.R.M. (eds.) CAV 2021. LNCS, vol. 12759, pp. 175–200. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-81685-8_8
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Benamira, A., Peyrin, T., Kuen-Yew, B.H. (2023). Truth-Table Net: A New Convolutional Architecture Encodable by Design into SAT Formulas. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds) Computer Vision – ECCV 2022 Workshops. ECCV 2022. Lecture Notes in Computer Science, vol 13801. Springer, Cham. https://doi.org/10.1007/978-3-031-25056-9_31
Download citation
DOI: https://doi.org/10.1007/978-3-031-25056-9_31
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-25055-2
Online ISBN: 978-3-031-25056-9
eBook Packages: Computer ScienceComputer Science (R0)