Abstract
We present an approach for the verification of feed-forward neural networks in which all nodes have a piece-wise linear activation function. Such networks are often used in deep learning and have been shown to be hard to verify for modern satisfiability modulo theory (SMT) and integer linear programming (ILP) solvers.
The starting point of our approach is the addition of a global linear approximation of the overall network behavior to the verification problem that helps with SMT-like reasoning over the network behavior. We present a specialized verification algorithm that employs this approximation in a search process in which it infers additional node phases for the non-linear nodes in the network from partial node phase assignments, similar to unit propagation in classical SAT solving. We also show how to infer additional conflict clauses and safe node fixtures from the results of the analysis steps performed during the search. The resulting approach is evaluated on collision avoidance and handwritten digit recognition case studies.
This work was supported by the Institutional Strategy of the University of Bremen, funded by the German Excellence Initiative.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
GNU Linear Programming Kit, http://www.gnu.org/software/glpk/glpk.html.
References
Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. 61, 85–117 (2015)
Yu, Q., Yang, Y., Song, Y., Xiang, T., Hospedales, T.M.: Sketch-a-net that beats humans. In: British Machine Vision Conference (BMVC), pp. 7.1–7.12 (2015)
Wagner, M., Koopman, P.: A philosophy for developing trust in self-driving cars. In: Meyer, G., Beiker, S. (eds.) Road Vehicle Automation 2. LNMOB, pp. 163–171. Springer, Cham (2015). doi:10.1007/978-3-319-19078-5_14
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). doi:10.1007/978-3-642-14295-6_24
Scheibler, K., Winterer, L., Wimmer, R., Becker, B.: Towards verification of artificial neural networks. In: 2015 MBMV Workshop, Chemnitz, Germany, pp. 30–40 (2015)
Scheibler, K., Neubauer, F., Mahdi, A., Fränzle, M., Teige, T., Bienmüller, T., Fehrer, D., Becker, B.: Accurate ICP-based floating-point reasoning. In: Formal Methods in Computer-Aided Design (FMCAD), pp. 177–184 (2016)
Katz, G., Barrett, C.W., 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). doi:10.1007/978-3-319-63387-9_5
Pulina, L., Tacchella, A.: Challenging SMT solvers to verify neural networks. AI Commun. 25(2), 117–135 (2012)
Huang, X., Kwiatkowska, M., Wang, S., Wu, M.: Safety verification of deep neural networks. In: Majumdar, R., Kunčak, V. (eds.) CAV 2017. LNCS, vol. 10426, pp. 3–29. Springer, Cham (2017). doi:10.1007/978-3-319-63387-9_1
Bastani, O., Ioannou, Y., Lampropoulos, L., Vytiniotis, D., Nori, A.V., Criminisi, A.: Measuring neural net robustness with constraints. In: Annual Conference on Neural Information Processing Systems (NIPS), pp. 2613–2621 (2016)
Chinneck, J.W., Dravnieks, E.W.: Locating minimal infeasible constraint sets in linear programs. INFORMS J. Comput. 3(2), 157–168 (1991)
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T.: Caffe: convolutional architecture for fast feature embedding. arXiv/CoRR 1408.5093 arXiv:1408.5093 (2014)
Franco, J., Martin, J.: A history of satisfiability. In: Handbook of Satisfiability. Frontiers in Artificial Intelligence and Applications, vol. 185, pp. 3–74. IOS Press, February 2009
Kroening, D., Strichman, O.: Decision Procedures - An Algorithmic Point of View. Springer, Heidelberg (2008)
Dutertre, B., de Moura, L.: A fast linear-arithmetic solver for DPLL(T). In: Ball, T., Jones, R.B. (eds.) CAV 2006. LNCS, vol. 4144, pp. 81–94. Springer, Heidelberg (2006). doi:10.1007/11817963_11
Eén, N., Sörensson, N.: An extensible SAT-solver. In: Giunchiglia, E., Tacchella, A. (eds.) SAT 2003. LNCS, vol. 2919, pp. 502–518. Springer, Heidelberg (2004). doi:10.1007/978-3-540-24605-3_37
Dutertre, B.: Yices 2.2. In: Biere, A., Bloem, R. (eds.) CAV 2014. LNCS, vol. 8559, pp. 737–744. Springer, Cham (2014). doi:10.1007/978-3-319-08867-9_49
Lecun, Y., Cortes, C.: The MNIST database of handwritten digits (2009)
Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Clevert, D., Unterthiner, T., Hochreiter, S.: Fast and accurate deep network learning by exponential linear units (ELUs). arXiv/CoRR 1511.07289 arXiv:1511.07289 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Ehlers, R. (2017). Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks. In: D'Souza, D., Narayan Kumar, K. (eds) Automated Technology for Verification and Analysis. ATVA 2017. Lecture Notes in Computer Science(), vol 10482. Springer, Cham. https://doi.org/10.1007/978-3-319-68167-2_19
Download citation
DOI: https://doi.org/10.1007/978-3-319-68167-2_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-68166-5
Online ISBN: 978-3-319-68167-2
eBook Packages: Computer ScienceComputer Science (R0)