Abstract
Formal verification of neural networks and broader machine learning models is an emerging field that has gained significant attention due to the growing use and impact of these data-driven methods. This track explores techniques for formally verifying neural networks and other machine learning models across various application domains. It includes papers and presentations discussing new methodologies, software frameworks, technical approaches, and case studies. Benchmarks play a crucial role in evaluating the effectiveness and scalability of these methods. Currently, available benchmarks mainly focus on computer vision problems, such as local robustness to adversarial perturbations of image classifiers. To address this limitation, this track compiles and publishes benchmarks comprising machine learning models and their specifications across domains such as computer vision, finance, security, and others. These benchmarks will help assess the suitability and applicability of formal verification methods in diverse domains.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bak, S., Liu, C., Johnson, T.: The second international verification of neural networks competition (VNN-COMP 2021): summary and results (2021). https://doi.org/10.48550/ARXIV.2109.00498
Bensalem, S., et al.: Continuous engineering for trustworthy learning-enabled autonomous systems. In: Steffen, B. (ed.) AISoLA 2023. LNCS, vol. 14380, pp. 256–278. Springer, Cham (2023)
Brix, C., Müller, M.N., Bak, S., Johnson, T.T., Liu, C.: First three years of the international verification of neural networks competition (VNN-COMP). Int. J. Softw. Tools Technol. Transfer 1–11 (2023)
Forets, M., Schilling, C.: The inverse problem for neural networks. In: Steffen, B. (ed.) AISoLA 2023. LNCS, vol. 14380, pp. 241–255. Springer, Cham (2023)
Johnson, T.T., et al.: ARCH-COMP21 category report: artificial intelligence and neural network control systems (AINNCS) for continuous and hybrid systems plants. In: Frehse, G., Althoff, M. (eds.) 8th International Workshop on Applied Verification of Continuous and Hybrid Systems (ARCH21). EPiC Series in Computing, vol. 80, pp. 90–119. EasyChair (2021). https://doi.org/10.29007/kfk9
Johnson, T.T., et al.: ARCH-COMP20 category report: artificial intelligence and neural network control systems (AINNCS) for continuous and hybrid systems plants. In: Frehse, G., Althoff, M. (eds.) ARCH20. 7th International Workshop on Applied Verification of Continuous and Hybrid Systems (ARCH20). EPiC Series in Computing, vol. 74, pp. 107–139. EasyChair (2020). https://doi.org/10.29007/9xgv
Katzke, T., Li, B., Klüttermann, S., Müller, E.: Towards verification of changes in dynamic machine learning models using deep ensemble anomaly detection. In: Steffen, B. (ed.) AISoLA 2023. LNCS, vol. 14380, p. 448. Springer, Cham (2023)
Kirov, D., Rollini, S.F.: Benchmark: remaining useful life predictor for aircraft equipment. In: Steffen, B. (ed.) AISoLA 2023. LNCS, vol. 14380, pp. 299–304. Springer, Cham (2023)
Kirov, D., Rollini, S.F., Chandrahas, R., Reddy, S., Chandupatla, Sawant, R.: Benchmark: object detection for maritime search and rescue. In: Steffen, B. (ed.) AISoLA 2023. LNCS, vol. 14380, pp. 305–310. Springer, Cham (2023)
Kirov, D., Rollini, S.F., Guglielmo, L.D., Cofer, D.: Formal verification of a neural network based prognostics system for aircraft equipment. In: Steffen, B. (ed.) AISoLA 2023. LNCS, vol. 14380, pp. 225–240. Springer, Cham (2023)
Lopez, D.M., et al.: ARCH-COMP22 category report: artificial intelligence and neural network control systems (AINNCS) for continuous and hybrid systems plants. In: Frehse, G., Althoff, M., Schoitsch, E., Guiochet, J. (eds.) Proceedings of 9th International Workshop on Applied Verification of Continuous and Hybrid Systems (ARCH22). EPiC Series in Computing, vol. 90, pp. 142–184. EasyChair (2022). https://doi.org/10.29007/wfgr
Lopez, D.M., Johnson, T.T.: Empirical analysis of benchmark generation for the verification of neural network image classifiers. In: Steffen, B. (ed.) AISoLA 2023. LNCS, vol. 14380, pp. 331–347. Springer, Cham (2023)
Lopez, D.M., et al.: ARCH-COMP19 category report: artificial intelligence and neural network control systems (AINNCS) for continuous and hybrid systems plants. In: Frehse, G., Althoff, M. (eds.) ARCH19. 6th International Workshop on Applied Verification of Continuous and Hybrid Systems. EPiC Series in Computing, vol. 61, pp. 103–119. EasyChair (2019). https://doi.org/10.29007/rgv8
Luo, Y., Ma, J., Han, S., Xie, L.: Benchmarks: semantic segmentation neural network verification and objection detection neural network verification in perceptions tasks of autonomous driving. In: Steffen, B. (ed.) AISoLA 2023. LNCS, vol. 14380, pp. 279–290. Springer, Cham (2023)
Lutz, S., Neider, D.: Benchmark: neural networks for anomaly detection in batch distillation. In: Steffen, B. (ed.) AISoLA 2023. LNCS, vol. 14380, pp. 449–452. Springer, Cham (2023)
Müller, M.N., Brix, C., Bak, S., Liu, C., Johnson, T.T.: The third international verification of neural networks competition (VNN-COMP 2022): summary and results (2022). https://doi.org/10.48550/arXiv.2212.10376
Pal, N., Lee, S., Johnson, T.T.: Benchmark: formal verification of semantic segmentation neural networks. In: Steffen, B. (ed.) AISoLA 2023. LNCS, vol. 14380, pp. 311–330. Springer, Cham (2023)
Robinette, P.K., Lopez, D.M., Johnson, T.T.: Benchmark: neural network malware classification. In: Steffen, B. (ed.) AISoLA 2023. LNCS, vol. 14380, pp. 291–298. Springer, Cham (2023)
Zaid, F.A., Diekmann, D., Neider, D.: Distribution-aware neuro-symbolic verification. In: Steffen, B. (ed.) AISoLA 2023. LNCS, vol. 14380, pp. 445–447. Springer, Cham (2023)
Acknowledgements
The material presented in this paper is based upon work supported by the National Science Foundation (NSF) through grant numbers 2220426 and 2220401, and the Defense Advanced Research Projects Agency (DARPA) under contract number FA8750-23-C-0518, and the Air Force Office of Scientific Research (AFOSR) under contract numbers FA9550-22-1-0019 and FA9550-23-1-0135. Any opinions, findings, conclusions, or recommendations expressed in this paper are those of the authors and do not necessarily reflect the views of AFOSR, DARPA, or NSF. In addition, the work was supported by the Deutsche Forschungsgemeinschaft (DFG) through grant number 459419731.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Neider, D., Johnson, T.T. (2024). Track C1: Safety Verification of Deep Neural Networks (DNNs). In: Steffen, B. (eds) Bridging the Gap Between AI and Reality. AISoLA 2023. Lecture Notes in Computer Science, vol 14380. Springer, Cham. https://doi.org/10.1007/978-3-031-46002-9_12
Download citation
DOI: https://doi.org/10.1007/978-3-031-46002-9_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-46001-2
Online ISBN: 978-3-031-46002-9
eBook Packages: Computer ScienceComputer Science (R0)