On Integer Programming for the Binarized Neural Network Verification Problem

References

• Amir G, Wu H, Barrett C, Katz G (2021) An SMT-based approach for verifying binarized neural networks. Groote JF, Larsen KG, eds. Tools Algorithms Construction Anal. Systems 28th Internat. Conf. (Springer, Cham, Switzerland), 203–222.Google Scholar
• Contardo C, Fukasawa R, Rousseau LM, Vidal T (2024) Optimal counterfactual explanations for k-nearest neighbors using mathematical optimization and constraint programming. Basu A, Mahjoub AR, Salazar González JJ, eds. Combin. Optim. 8th Internat. Sympos. (Springer, Cham, Switzerland), 318–331.Google Scholar
• Fischetti M, Jo J (2018) Deep neural networks and mixed integer linear optimization. Constraints 23(3):296–309.Google Scholar
• Han S, Gómez A (2021) Single-neuron convexification for binarized neural networks. Accessed May 27, 2021, https://optimization-online.org/wp-content/uploads/2021/05/8419.pdf.Google Scholar
• Hubara I, Courbariaux M, Soudry D, El-Yaniv R, Bengio Y (2016) Binarized neural networks. Lee D, Sugiyama M, von Luxburg U, Guyon I, Garnett R, eds. Adv. Neural Inform. Processing Systems, vol. 29 (Curran Associates Inc., Red Hook, NY), 4107–4115.Google Scholar
• Ivashchenko M, Choi SW, Nguyen LV, Tran HD (2023) Verifying binary neural networks on continuous input space using star reachability. IEEE Internat. Conf. Formal Methods Software Engrg. (IEEE, Piscataway, NJ), 7–17.Google Scholar
• Jia K, Rinard M (2020) Efficient exact verification of binarized neural networks. Larochelle H, Ranzato M, Hadsell R, Balcan MF, Lin HT, eds. Adv. Neural Inform. Processing Systems, vol. 33 (Curran Associates Inc., Red Hook, NY), 1782–1795.Google Scholar
• Khalil EB, Gupta A, Dilkina B (2019) Combinatorial attacks on binarized neural networks. Internat. Conf. Learn. Representations (ICLR, Appleton, WI).Google Scholar
• Kovásznai G, Gajdár K, Narodytska N (2021) Portfolio solver for verifying binarized neural networks. Ann. Math. Inform. 53:183–200.Google Scholar
• Kung J, Zhang D, van der Wal G, Chai S, Mukhopadhyay S (2018) Efficient object detection using embedded binarized neural networks. J. Signal Processing Systems 90(6):877–890.Google Scholar
• Lubczyk D, Neto J (2024) Neuron pairs in binarized neural networks robustness verification via integer linear programming. Basu A, Mahjoub AR, Salazar González JJ, eds. Combinatorial Optimization (Springer), 305–317.Google Scholar
• Ma Y, Xiong H, Hu Z, Ma L (2019) Efficient super resolution using binarized neural network. IEEE/CVF Conf. Comput. Vision Pattern Recognition Workshops (IEEE, Piscataway, NJ), 694–703.Google Scholar
• McDanel B, Teerapittayanon S, Kung HT (2017) Embedded binarized neural networks. Gunningberg P, Voigt T, Mottola L, Lu C, eds. Proc. Internat. Conf. Embedded Wireless Systems Networks (Junction Publishing, Canada), 168–173.Google Scholar
• Mothilal R, Sharma A, Tan C (2020) Explaining machine learning classifiers through diverse counterfactual explanations. Hildebrandt M, Castillo C, Celis E, Ruggieri S, Taylor L, Zanfir-Fortuna G, eds. Conf. Fairness Accountability Transparency (ACM, New York), 607–617.Google Scholar
• Narodytska N, Kasiviswanathan S, Ryzhyk L, Sagiv M, Walsh T (2018) Verifying properties of binarized deep neural networks. McIlraith S, Weinberger K, eds. Proc. AAAI Conf. Artificial Intelligence, vol. 32 (AAAI, Palo Alto, CA), 6615–6624.Google Scholar
• Shih A, Darwiche A, Choi A (2019) Verifying binarized neural networks by Angluin-style learning. Janota M, Lynce I, eds. Theory Appl. Satisfiability Testing – SAT 2019: 22nd Internat. Conf. (Springer, Cham, Switzerland), 354–370.Google Scholar
• Shridhar K, Jain H, Agarwal A, Kleyko D (2020) End to end binarized neural networks for text classification. Moosavi NS, Fan A, Shwartz V, Glavaš G, Joty S, Wang A, Wolf T, eds. Proc. SustaiNLP Workshop Simple Efficient Natural Language Processing (Association for Computational Linguistics, Stroudsburg, PA), 29–34.Google Scholar
• Vivier-Ardisson G, Forel A, Parmentier A, Vidal T (2024) CF-OPT: Counterfactual explanations for structured prediction. Preprint, submitted May 28, https://arxiv.org/abs/2405.18293.Google Scholar
• Wachter S, Mittelstadt B, Russell C (2018) Counterfactual explanations without opening the black box: Automated decisions and the GDPR. Harvard J. Law Tech. 31(2):841–888.Google Scholar
• Zhang Y, Zhao Z, Chen G, Song F, Chen T (2021) BDD4BNN: A BDD-based quantitative analysis framework for binarized neural networks. Silva A, Leino KRM, eds. Comput. Aided Verification 33rd Internat. Conf. (Springer, Cham, Switzerland), 175–200.Google Scholar