Abstract
The verification of the security of neural networks is cruicial, especially for the field of autonomous driving. Although there are currently benchmarks for the verification of the robustness of neural networks, there are hardly any benchmarks related to the field of autonomous driving, especially those related to object detection and semantic segmentation. Thus, a notable gap exists in formally verifying the robustness of semantic semantic segmentation and object detection tasks under complex, real-world conditions. To address this, we present an innovative approach to benchamark formal verification for autonomous driving perception tasks. Firstly, we propose robust verification benchmarks for semantic segmentation and object detection, supplementing existing methods. Secondly, and more significantly, we introduce a novel patch-level disturbance approach for object detection, providing a more realistic representation of real-world scenarios. By augmenting the current verification benchmarks with our novel proposals, our work contributes towards developing a more comprehensive, practical, and realistic benchmarking methodology for perception tasks in autonomous driving, thereby propelling the field towards improved safety and reliability. Our dataset and code used in this work are publicly available.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
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, PLDI 2019, pp. 731–744. Association for Computing Machinery, New York (2019)
Bak, S.: nnenum: verification of ReLU neural networks with optimized abstraction refinement. In: Dutle, A., Moscato, M.M., Titolo, L., Muñoz, C.A., Perez, I. (eds.) NFM 2021. LNCS, vol. 12673, pp. 19–36. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-76384-8_2
Bak, S., Liu, C., Johnson, T.T.: The second international verification of neural networks competition (vnn-comp 2021): Summary and results. arXiv: 2109.00498 (2021)
Bijelic, M., et al.: Seeing through fog without seeing fog: deep multimodal sensor fusion in unseen adverse weather. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11679–11689 (2020)
Botoeva, E., Kouvaros, P., Kronqvist, J., Lomuscio, A., Misener, R.: Efficient verification of relu-based neural networks via dependency analysis. In: AAAI Conference on Artificial Intelligence (2020)
Shaler, B.: DanGill, M.M.M.P.W.C.: Carvana image masking challenge (2017)
Brix, C., Noll, T.: Debona: decoupled boundary network analysis for tighter bounds and faster adversarial robustness proofs. arXiv: 2006.09040 (2020)
Brix, C., Muller, M.N., Bak, S., Johnson, T.T., Liu, C.: First three years of the international verification of neural networks competition (vnn-comp). ArXiv, abs/ arXiv: 2301.05815 (2023)
Caesar, H., et al.: nuscenes: A multimodal dataset for autonomous driving. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11618–11628 (2019)
Chahal, K.S., Dey, K.: A survey of modern object detection literature using deep learning. ArXiv, abs/ arXiv: 1808.07256 (2018)
Chan, R., et al.: Segmentmeifyoucan: A benchmark for anomaly segmentation. ArXiv, abs/ arXiv: 2104.14812 (2021)
Dathathri, S., et al.: Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol. 33, pp. 5318–5331. Curran Associates Inc. (2020)
Diaz-Ruiz, C.A., et al.: Ithaca365: dataset and driving perception under repeated and challenging weather conditions. In: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 21351–21360 (2022)
Dong, Y., et al.: Benchmarking robustness of 3d object detection to common corruptions in autonomous driving. ArXiv, abs/ arXiv: 2303.11040 (2023)
Fazlyab, M., Morari, M., Pappas, G.J.: Safety verification and robustness analysis of neural networks via quadratic constraints and semidefinite programming. IEEE Trans. Autom. Control 67(1), 1–15 (2022)
Ferrari, C., Mueller, M.N., Jovanović, N., Vechev, M.: Complete verification via multi-neuron relaxation guided branch-and-bound. In: International Conference on Learning Representations (2022)
Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? the kitti vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354–3361 (2012)
Hendrycks, D., Basart, S., Mazeika, M., Mostajabi, M., Steinhardt, J., Song, D.X.: Scaling out-of-distribution detection for real-world settings. In: International Conference on Machine Learning (2022)
Henriksen, P., Lomuscio, A.: Efficient neural network verification via adaptive refinement and adversarial search (2020)
Henriksen, P., Lomuscio, A.: Deepsplit: an efficient splitting method for neural network verification via indirect effect analysis. In: Zhou, Z.-H. (ed.) Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI 2021, pp. 2549–2555. International Joint Conferences on Artificial Intelligence Organization, Main Track (Aug 2021)
Henriksen, P., Hammernik, K., Rueckert, D., Lomuscio, A.: Bias field robustness verification of large neural image classifiers. In: British Machine Vision Conference (2021)
Huang, C., Fan, J., Li, W., Chen, X., Zhu, Q.: Reachnn: reachability analysis of neural-network controlled systems. ACM Trans. Embed. Comput. Syst. 18(5s) (2019)
Ivanov, R., Weimer, J., Alur, R., Pappas, G. J., Lee, I.: Verisig: verifying safety properties of hybrid systems with neural network controllers. In: Proceedings of the 22nd ACM International Conference on Hybrid Systems: Computation and Control, HSCC 2019, pp. 169–178. Association for Computing Machinery, New York (2019)
Katz, G., et al.: 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
Katz, S.M., Corso, A., Strong, C.A., Kochenderfer, M.J.: Verification of image-based neural network controllers using generative models. In: 2021 IEEE/AIAA 40th Digital Avionics Systems Conference (DASC), pp. 1–10 (2021)
Khedr, H., Ferlez, J., Shoukry, Y.: Effective formal verification of neural networks using the geometry of linear regions. ArXiv, abs/ arXiv: 2006.10864 (2020)
Li, K., et al.: A real-world road corner case dataset for object detection in autonomous driving. ArXiv, abs/ arXiv: 2203.07724 (2022)
Liu, X., Yang, H., Liu, Z., Song, L., Chen, Y., Li, H.H.: Dpatch: an adversarial patch attack on object detectors. In: Computer Vision and Pattern Recognition (2018)
Ma, X.: dog-qiuqiu/yolo-fastestv2: V0.2 (August 2021)
Mohapatra, J., Weng, T.-W., Chen, P.-Y., Liu, S., Daniel, L.: Towards verifying robustness of neural networks against a family of semantic perturbations. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 241–249 (2020)
Muller, 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 (2023)
Pinggera, P., Ramos, S., Gehrig, S., Franke, U., Rother, C., Mester, R.: Lost and found: detecting small road hazards for self-driving vehicles. In: 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1099–1106 (2016)
Pitropov, M.A., et al.: Canadian adverse driving conditions dataset. Inter. J. Robo. Res. 40, 681–690 (2020)
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. ArXiv, abs/ arXiv: 1505.04597 (2015)
Ruan, W., Wu, M., Sun, Y., Huang, X., Kroening, D., Kwiatkowska, M.: Global robustness evaluation of deep neural networks with provable guarantees for L0 norm. CoRR, abs/ arXiv: 1804.05805 (2018)
Salman, H., Yang, G., Zhang, H., Hsieh, C.-J., Zhang, P.: A convex relaxation barrier to tight robustness verification of neural networks. Adv. Neural. Inf. Process. Syst. 32, 9835–9846 (2019)
Shen, J.,et al.: Sok: on the semantic ai security in autonomous driving. ArXiv, abs/ arXiv: 2203.05314 (2022)
Singh, G., Gehr, T., Püschel, M., Vechev, M.: An abstract domain for certifying neural networks. Proc. ACM Program. Lang. 3(POPL) (2019)
Sun, P., Kretzschmar, H., et al.: Scalability in perception for autonomous driving: Waymo open dataset. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2443–2451 (2020)
Thoma, M.: A survey of semantic segmentation. ArXiv, abs/ arXiv: 1602.06541 (2016)
Tjeng, V., Xiao, K. Y., Tedrake, R.: Evaluating robustness of neural networks with mixed integer programming. In: International Conference on Learning Representations (2017)
Tran, H.-D., Cai, F., Diego, M. L., Musau, P., Johnson, T.T., Koutsoukos, X.: Safety verification of cyber-physical systems with reinforcement learning control. ACM Trans. Embed. Comput. Syst., 18(5s) (2019)
Tran, H.-D., Bak, S., Xiang, W., Johnson, T.T.: Verification of deep convolutional neural networks using imagestars. In: Lahiri, S.K., Wang, C. (eds.) CAV 2020. LNCS, vol. 12224, pp. 18–42. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-53288-8_2
Tran, H.-D., et al.: Robustness verification of semantic segmentation neural networks using relaxed reachability. In: Silva, A., Leino, K.R.M. (eds.) CAV 2021. LNCS, vol. 12759, pp. 263–286. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-81685-8_12
Wang, S., et al.: Beta-CROWN: efficient bound propagation with per-neuron split constraints for complete and incomplete neural network verification. In: Advances in Neural Information Processing Systems 34 (2021)
Xu, K., et al.: Automatic perturbation analysis for scalable certified robustness and beyond. In: Advances in Neural Information Processing Systems 33 (2020)
Xu, K., et al.: Fast and complete: enabling complete neural network verification with rapid and massively parallel incomplete verifiers. In: International Conference on Learning Representations (2021)
Yurtsever, E., Lambert, J., Carballo, A., Takeda, K.: A survey of autonomous driving: common practices and emerging technologies. IEEE Access 8, 58443–58469 (2019)
Zhang, H., Weng, T.-W., Chen, P.-Y., Hsieh, C.-J., Daniel, L.: Efficient neural network robustness certification with general activation functions. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems, NIPS 2018, pp. 4944–4953. Curran Associates Inc., Red Hook (2018)
Zhang, H., et al.: General cutting planes for bound-propagation-based neural network verification. In: Advances in Neural Information Processing Systems (2022)
Zhang, H., et al.: A branch and bound framework for stronger adversarial attacks of ReLU networks. In: Proceedings of the 39th International Conference on Machine Learning, vol. 162, pp. 26591–26604 (2022)
Zhang, J., Zou, X., Kuang, L., Wang, J., Sherratt, R., Yu, X.: Cctsdb 2021: a more comprehensive traffic sign detection benchmark. Human-centric Comput. Inform. Sci. 12, 23 (2022)
Acknowledgement
Yonggang Luo was supported by the Department of Human Resources and Social Security of Chongqing City, through the Chongqing Liuchuang Program. Sanchu Han was supported by the Department of Human Resources and Social Security of Chongqing City, through the Chongqing Talents Program.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendices
A Network Details
In our benchmarks, we used a total of three networks, namely Unet\(\_\)simp, Unet\(\_\)upsample, and Yolo. Among them, Unet\(\_\)simp and Unet\(\_\)upsample correspond to benchmark Carvana Unet, while Yolo corresponds to benchmark CCTSDB YOLO. We have summarized the amount of parameters and the size of the models corresponding to these thress networks in the Table 2. The networks in benchmark Carvana Unet used operation such as Conv, BN, ReLu, AvgPool, ConvTranspose, etc., whereas the networks in benchmark CCTSDB YOLO used operations like Conv, BN, ReLu, MaxPool, interpolate, etc.
B Implementation Details
For the benchmark Carvana Unet, we used the RMSprop optimizer, where the weight decay was set to \(1 \times 10^{-8}\) and the momentum was set to 0.9. We initialized the learning rate to \(1 \times 10^{-5}\), with a decay strategy of ReduceLROnPlateau, where the mode was chosen as max and patience was set to 2. We trained it for a total of 5 epochs.
For the benchmark CCTSDB YOLO, we used the SGD optimizer, where the weight decay was set to 0.0005 and the momentum was set to 0.949. We initialized the learning rate to 0.001, with a decay strategy of MultiStepLR, where the milestones was set to an array as [150, 250] and gamma was set to 0.1. We trained it for a total of 300 epochs.
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Luo, Y., Ma, J., Han, S., Xie, L. (2024). Benchmarks: Semantic Segmentation Neural Network Verification and Objection Detection Neural Network Verification in Perceptions Tasks of Autonomous Driving. 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_16
Download citation
DOI: https://doi.org/10.1007/978-3-031-46002-9_16
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)