Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content
SpringerLink
Log in

DeepCDCL: A CDCL-based Neural Network Verification Framework

  • Conference paper
  • First Online:
Theoretical Aspects of Software Engineering (TASE 2024)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 14777))

Included in the following conference series:

  • 228 Accesses

Abstract

Neural networks in safety-critical applications face increasing security and safety concerns due to their susceptibility to little disturbance. In this paper, we propose DeepCDCL, a novel neural network verification framework based on the Conflict-Driven Clause Learning (CDCL) algorithm. We introduce an asynchronous clause learning and management structure, reducing redundant time consumption compared to the direct application of the CDCL framework. Furthermore, we also provide a detailed evaluation of the performance of our approach on the ACAS Xu and MNIST datasets, showing a significant speed-up in most verification problems.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 79.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Anderson, G., Pailoor, S., Dillig, I., Chaudhuri, S.: Optimization and abstraction: a synergistic approach for analyzing neural network robustness. In: Proceedings of the 40th ACM SIGPLAN Conference on Programming Language Design and Implementation, pp. 731–744 (2019)

    Google Scholar 

  2. Ashok, P., Hashemi, V., Kretínský, J., Mohr, S.: DeepAbstract: neural network abstraction for accelerating verification. In: Hung, D.V., Sokolsky, O. (eds.) Automated Technology for Verification and Analysis - 18th International Symposium, ATVA 2020, Hanoi, Vietnam, 19–23 October 2020, Proceedings, LNCS, vol. 12302, pp. 92–107. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59152-6_5

  3. Bastani, O., Ioannou, Y., Lampropoulos, L., Vytiniotis, D., Nori, A., Criminisi, A.: Measuring neural net robustness with constraints. In: Advances in Neural Information Processing Systems, vol. 29 (2016)

    Google Scholar 

  4. Bertsimas, D., Tsitsiklis, J.N.: Introduction to linear optimization, vol. 6. Athena scientific Belmont, MA (1997)

    Google Scholar 

  5. Boopathy, A., Weng, T., Chen, P., Liu, S., Daniel, L.: Cnn-cert: an efficient framework for certifying robustness of convolutional neural networks. In: The Thirty-Third AAAI Conference on Artificial Intelligence, AAAI 2019, The Thirty-First Innovative Applications of Artificial Intelligence Conference, IAAI 2019, The Ninth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019, Honolulu, Hawaii, USA, January 27 - February 1, 2019. pp. 3240–3247. AAAI Press (2019).https://doi.org/10.1609/aaai.v33i01.33013240

  6. Brix, C., Bak, S., Liu, C., Johnson, T.T.: The fourth international verification of neural networks competition (vnn-comp 2023): summary and results (2023)

    Google Scholar 

  7. Chinneck, J.W., Dravnieks, E.W.: Locating minimal infeasible constraint sets in linear programs. INFORMS J. Comput. 3, 157–168 (1991). https://api.semanticscholar.org/CorpusID:207225476

  8. Deng, L.: The MNIST database of handwritten digit images for machine learning research. IEEE Signal Process. Mag. 29(6), 141–142 (2012)

    Article  Google Scholar 

  9. 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

    Chapter  Google Scholar 

  10. Ferrari, C., Müller, M.N., Jovanovic, N., Vechev, M.T.: Complete verification via multi-neuron relaxation guided branch-and-bound. In: The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, 25–29 April 2022. OpenReview.net (2022). https://openreview.net/forum?id=l_amHf1oaK

  11. 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)

    Google Scholar 

  12. Gopinath, D., Katz, G., Păsăreanu, C.S., Barrett, C.: DeepSafe: a data-driven approach for assessing robustness of neural networks. In: Lahiri, S.K., Wang, C. (eds.) ATVA 2018. LNCS, vol. 11138, pp. 3–19. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01090-4_1

    Chapter  Google Scholar 

  13. Gowal, S., et al.: Scalable verified training for provably robust image classification. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 4842–4851 (2019)

    Google Scholar 

  14. Gurobi Optimization, L.: Gurobi optimizer reference manual (2021). http://www.gurobi.com

  15. 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). https://doi.org/10.1007/978-3-319-63387-9_1

    Chapter  Google Scholar 

  16. Julian, K.D., Kochenderfer, M.J., Owen, M.P.: Deep neural network compression for aircraft collision avoidance systems. J. Guid. Control. Dyn. 42(3), 598–608 (2019)

    Article  Google Scholar 

  17. 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)

    Google Scholar 

  18. 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

    Chapter  Google Scholar 

  19. Katz, G., Huang, D.A., Ibeling, D., Julian, K., Lazarus, C., Lim, R., Shah, P., Thakoor, S., Wu, H., Zeljić, A., Dill, D.L., Kochenderfer, M.J., Barrett, C.: The marabou framework for verification and analysis of deep neural networks. In: Dillig, I., Tasiran, S. (eds.) CAV 2019. LNCS, vol. 11561, pp. 443–452. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-25540-4_26

    Chapter  Google Scholar 

  20. The marabou framework for verification and analysis of deep neural networks. In: CAV 2019. LNCS, vol. 11561, pp. 443–452. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-25540-4_26

  21. Khedr, H., Ferlez, J., Shoukry, Y.: PEREGRiNN: penalized-relaxation greedy neural network verifier. In: Silva, A., Leino, K.R.M. (eds.) CAV 2021. LNCS, vol. 12759, pp. 287–300. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-81685-8_13

    Chapter  Google Scholar 

  22. Li, J., Liu, J., Yang, P., Chen, L., Huang, X., Zhang, L.: Analyzing deep neural networks with symbolic propagation: towards higher precision and faster verification. In: Chang, B.-Y.E. (ed.) SAS 2019. LNCS, vol. 11822, pp. 296–319. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32304-2_15

    Chapter  Google Scholar 

  23. Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. In: ICLR 2018. OpenReview.net, Vancouver, BC, Canada (2018)

    Google Scholar 

  24. Marques-Silva, J., Lynce, I., Malik, S.: Conflict-driven clause learning sat solvers. In: Handbook of Satisfiability, pp. 133–182. IOS press (2021)

    Google Scholar 

  25. 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)

    Google Scholar 

  26. de Moura, L., Bjørner, N.: Z3: an efficient SMT solver. In: Ramakrishnan, C.R., Rehof, J. (eds.) TACAS 2008. LNCS, vol. 4963, pp. 337–340. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-78800-3_24

    Chapter  Google Scholar 

  27. 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)

    Google Scholar 

  28. Nieuwenhuis, R., Oliveras, A., Tinelli, C.: Solving SAT and SAT modulo theories: from an abstract davis–putnam–logemann–loveland procedure to dpll(T). J. ACM 53(6), 937–977 (2006). https://doi.org/10.1145/1217856.1217859

  29. 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

    Chapter  Google Scholar 

  30. Sebastiani, R.: Lazy satisability modulo theories. J. Satisf. Boolean Model. Comput. 3(3-4), 141–224 (2007). https://doi.org/10.3233/SAT190034

  31. 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)

    Google Scholar 

  32. 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)

    Google Scholar 

  33. Singh, G., Gehr, T., Püschel, M., Vechev, M.: Boosting robustness certification of neural networks. In: International conference on learning representations (2018)

    Google Scholar 

  34. Singh, G., Gehr, T., Püschel, M., Vechev, M.T.: An abstract domain for certifying neural networks. PACMPL 3(POPL), 41:1–41:30 (2019)

    Google Scholar 

  35. Tjeng, V., Xiao, K.Y., Tedrake, R.: Evaluating robustness of neural networks with mixed integer programming. In: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, 6–9 May 2019. OpenReview.net (2019). https://openreview.net/forum?id=HyGIdiRqtm

  36. Tran, H.-D., Yang, X., Manzanas Lopez, D., Musau, P., Nguyen, L.V., Xiang, W., Bak, S., Johnson, T.T.: NNV: the neural network verification tool for deep neural networks and learning-enabled cyber-physical systems. In: Lahiri, S.K., Wang, C. (eds.) CAV 2020. LNCS, vol. 12224, pp. 3–17. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-53288-8_1

    Chapter  Google Scholar 

  37. Urmson, C., Whittaker, W.: Self-driving cars and the urban challenge. IEEE Intell. Syst. 23(2), 66–68 (2008)

    Article  Google Scholar 

  38. Wang, S., Pei, K., Whitehouse, J., Yang, J., Jana, S.: Efficient formal safety analysis of neural networks. In: Advances in Neural Information Processing Systems, vol. 31 (2018)

    Google Scholar 

  39. Wang, S., Pei, K., Whitehouse, J., Yang, J., Jana, S.: Formal security analysis of neural networks using symbolic intervals. In: 27th USENIX Security Symposium (USENIX Security 18), pp. 1599–1614 (2018)

    Google Scholar 

  40. Wang, S., Zhang, H., Xu, K., Lin, X., Jana, S., Hsieh, C.J., Kolter, J.Z.: Beta-CROWN: efficient bound propagation with per-neuron split constraints for neural network robustness verification. Adv. Neural. Inf. Process. Syst. 34, 29909–29921 (2021)

    Google Scholar 

  41. Weng, L., et al.: Towards fast computation of certified robustness for ReLu networks. In: International Conference on Machine Learning, pp. 5276–5285. PMLR (2018)

    Google Scholar 

  42. Weng, T., et al.: Evaluating the robustness of neural networks: An extreme value theory approach. In: 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30–May 3, 2018, Conference Track Proceedings. OpenReview.net (2018). https://openreview.net/forum?id=BkUHlMZ0b

  43. Xu, K., et al.: Fast and complete: enabling complete neural network verification with rapid and massively parallel incomplete verifiers. In: 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, 3–7 May 2021. OpenReview.net (2021). https://openreview.net/forum?id=nVZtXBI6LNn

  44. Yang, P., et al.: Improving neural network verification through spurious region guided refinement. In: TACAS 2021. LNCS, vol. 12651, pp. 389–408. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-72016-2_21

    Chapter  Google Scholar 

  45. Yin, B., Chen, L., Liu, J., Wang, J.: Efficient complete verification of neural networks via layerwised splitting and refinement. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 41(11), 3898–3909 (2022). https://doi.org/10.1109/TCAD.2022.3197534

    Article  Google Scholar 

  46. Zhang, H., et al.: Towards stable and efficient training of verifiably robust neural networks. arXiv preprint arXiv:1906.06316 (2019)

  47. Zhang, H., et al.: General cutting planes for bound-propagation-based neural network verification. In: NeurIPS (2022). http://papers.nips.cc/paper_files/paper/2022/hash/0b06c8673ebb453e5e468f7743d8f54e-Abstract-Conference.html

Download references

Acknowledgement

This work was partially supported by CAS Project for Young Scientists in Basic Research, Grant No. YSBR-040, ISCAS New Cultivation Project ISCAS-PYFX-202201, and ISCAS Basic Research ISCAS-JCZD-202302.

Author information

Authors and Affiliations

  1. Key Laboratory of System Software (Chinese Academy of Sciences) and State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing, China

    Zongxin Liu, Pengfei Yang & Lijun Zhang

  2. University of Chinese Academy of Sciences, Beijing, China

    Zongxin Liu & Lijun Zhang

  3. The University of Liverpool, Liverpool, UK

    Xiaowei Huang

Authors
  1. Zongxin Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Pengfei Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Lijun Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Xiaowei Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Lijun Zhang .

Editor information

Editors and Affiliations

  1. National University of Singapore, Singapore, Singapore

    Wei-Ngan Chin

  2. Shenzhen University, Guangdong, China

    Zhiwu Xu

Rights and permissions

Reprints and permissions

Copyright information

© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Liu, Z., Yang, P., Zhang, L., Huang, X. (2024). DeepCDCL: A CDCL-based Neural Network Verification Framework. In: Chin, WN., Xu, Z. (eds) Theoretical Aspects of Software Engineering. TASE 2024. Lecture Notes in Computer Science, vol 14777. Springer, Cham. https://doi.org/10.1007/978-3-031-64626-3_20

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-64626-3_20

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-64625-6

  • Online ISBN: 978-3-031-64626-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation