Page 36 - 《软件学报》2025年第8期

刘宗鑫 等: 神经网络的增量验证 3459

[16] Sun B, Sun J, Pham LH, Shi J. Causality-based neural network repair. In: Proc. of the 44th Int’l Conf. on Software Engineering.
Pittsburgh: ACM, 2022. 338–349. [doi: 10.1145/3510003.3510080]
[17] Ashok P, Hashemi V, Křetínský J, Mohr S. DeepAbstract: Neural network abstraction for accelerating verification. In: Proc. of the 18th
Int’l Symp. Hanoi: Springer, 2020. 92–107. [doi: 10.1007/978-3-030-59152-6_5]
[18] Elboher YY, Gottschlich J, Katz G. An abstraction-based framework for neural network verification. In: Lahiri S K, Wang C, eds.
Computer Aided Verification. Cham: Springer, 2020. 43–65. [doi: 10.1007/978-3-030-53288-8_3]
[19] Ostrovsky M, Barrett C, Katz G. An abstraction-refinement approach to verifying convolutional neural networks. In: Bouajjani A, Holík L,
Wu ZL, eds. Automated Technology for Verification and Analysis. Cham: Springer, 2022. 391–396. [doi: 10.1007/978-3-031-19992-9_25]
[20] Ganin Y, Ustinova E, Ajakan H, Germain P, Larochelle H, Laviolette F, Marchand M, Lempitsky V. Domain-adversarial training of
neural networks. In: Csurka G, ed. Domain Adaptation in Computer Vision Applications. Cham: Springer, 2017. 189–209. [doi: 10.1007/
978-3-319-58347-1_10]
[21] Liu YQ, Ma SQ, Aafer Y, Lee WC, Zhai J, Wang WH, Zhang XY. Trojaning attack on neural networks. In: Proc. of the 25th Annual
Network and Distributed System Security Symp. San Diego: The Internet Society, 2018.
[22] Yang PF, Li RJ, Li JL, Huang CC, Wang JY, Sun J, Xue B, Zhang LJ. Improving neural network verification through spurious region
guided refinement. In: Groote JF, Larsen KG, eds. Tools and Algorithms for the Construction and Analysis of Systems. Cham: Springer,
2021. 389–408. [doi: 10.1007/978-3-030-72016-2_21]
[23] Ugare S, Banerjee D, Misailovic S, Singh G. Incremental verification of neural networks. Proc. of the ACM on Programming Languages,
2023, 7(PLDI): 185. [doi: 10.1145/3591299]
[24] Sotoudeh M, Thakur AV. Provable repair of deep neural networks. In: Proc. of the 42nd ACM SIGPLAN Int’l Conf. on Programming
Language Design and Implementation. ACM, 2021. 588–603. [doi: 10.1145/3453483.3454064]
[25] Ma JN, Yang PF, Wang JY, Sun YC, Huang CC, Wang Z. VeRe: Verification guided synthesis for repairing deep neural networks. In:
Proc. of the 46th IEEE/ACM Int’l Conf. on Software Engineering. Lisbon Portugal: ACM, 2024. 8. [doi: 10.1145/3597503.3623332]
[26] Xu KS, Zhang H, Wang SQ, Wang YH, Jana S, Lin X, Hsieh CJ. Fast and complete: Enabling complete neural network verification with
rapid and massively parallel incomplete verifiers. In: Proc. of the 9th Int’l Conf. on Learning Representations. OpenReview.net, 2021.
[27] Madry A, Makelov A, Schmidt L, Tsipras D, Vladu A. Towards deep learning models resistant to adversarial attacks. In: Proc. of the 6th
Int’l Conf. on Learning Representations. Vancouver: OpenReview.net, 2018.
[28] Singh G, Gehr T, Mirman M, Püschel M, Vechev M. Fast and effective robustness certification. In: Proc. of the 32nd Int’l Conf. on
Neural Information Processing Systems. Montréal: Curran Associates Inc., 2018. 10825–10836.
[29] Pulina L, Tacchella A. An abstraction-refinement approach to verification of artificial neural networks. In: Touili T, Cook B, Jackson P,
eds. Computer Aided Verification. Berlin, Heidelberg: Springer, 2010. 243–257. [doi: 10.1007/978-3-642-14295-6_24]
[30] Lomuscio A, Maganti L. An approach to reachability analysis for feed-forward ReLU neural networks. arXiv: 1706.07351, 2017.
[31] Narodytska N, Kasiviswanathan S, Ryzhyk L, Sagiv M, Walsh T. Verifying properties of binarized deep neural networks. In: Proc. of the
32nd AAAI Conf. on Artificial Intelligence. New Orleans: AAAI, 2018. 6615–6624. [doi: 10.1609/aaai.v32i1.12206]
[32] Bunel R, Turkaslan I, Torr PHS, Kumar MP, Lu JY, Kohli P. Branch and bound for piecewise linear neural network verification. The
Journal of Machine Learning Research, 2020, 21(1): 42.
[33] Lin W, Yang ZF, Chen X, Zhao QY, Li XK, Liu ZM, He JF. Robustness verification of classification deep neural networks via linear
programming. In: Proc. of the 2019 IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR). Long Beach: IEEE, 2019.
11410–11419. [doi: 10.1109/CVPR.2019.01168]
[34] Müller C, Serre F, Singh G, Püschel M, Vechev MT. Scaling polyhedral neural network verification on GPUs. In: Proc. of the 4th Conf.
on Machine Learning and Systems. MLSys, 2021.
[35] Singh G, Ganvir R, Püschel M, Vechev M. Beyond the single neuron convex barrier for neural network certification. In: Proc. of the 33rd
Int’l Conf. on Neural Information Processing Systems. Vancouver: Curran Associates Inc., 2019. 1352.
[36] Li JL, Liu JC, Yang P, Chen LQ, Huang XW, Zhang LJ. Analyzing deep neural networks with symbolic propagation: Towards higher
precision and faster verification. In: Proc. of the 26th Int’l Symp. Porto: Springer, 2019. 296–319. [doi: 10.1007/978-3-030-32304-2_15]
[37] Huang XW, Kwiatkowska M, Wang S, Wu M. Safety verification of deep neural networks. In: Majumdar R, Kunčak V, eds. Computer
Aided Verification. Cham: Springer, 2017. 3–29. [doi: 10.1007/978-3-319-63387-9_1]
[38] Ruan WJ, Huang XW, Kwiatkowska M. Reachability analysis of deep neural networks with provable guarantees. In: Proc. of the 27th Int’l
Joint Conf. on Artificial Intelligence. Stockholm: AAAI Press, 2018. 2651–2659.
[39] Dutta S, Jha S, Sankaranarayanan S, Tiwari A. Output range analysis for deep feedforward neural networks. In: Dutle A, Muñoz C,