Logic gate neural networks are good for verification

conference paper Logic gate neural networks are good for verification PMLR published yes Fabian Kresse author faff3c84-23f6-11ef-9085-e5187b51c604 Zhengqi Yu author 20aa2ae8-f2f1-11ed-bbfa-8205053f1342 Christoph Lampert author 40C20FD2-F248-11E8-B48F-1D18A9856A870000-0001-8622-7887 Thomas A Henzinger author 40876CD8-F248-11E8-B48F-1D18A9856A870000-0002-2985-7724 ChLa department ToHe department NeuS: International Conferenceon Neuro-Symbolic Systems Vigilant Algorithmic Monitoring of Software project Learning-based systems are increasingly deployed across various domains, yet the complexity of traditional neural networks poses significant challenges for formal verification. Unlike conventional neural networks, learned Logic Gate Networks (LGNs) replace multiplications with Boolean logic gates, yielding a sparse, netlist-like architecture that is inherently more amenable to symbolic verification, while still delivering promising performance. In this paper, we introduce a SAT encoding for verifying global robustness and fairness in LGNs. We evaluate our method on five benchmark datasets, including a newly constructed 5-class variant, and find that LGNs are both verification-friendly and maintain strong predictive performance. https://research-explorer.ista.ac.at/download/20296/20314/2025_NeuS_Kresse.pdf application/pdfno ML Research Press2025Philadephia, PA, United States eng 2nd International Conferenceon Neuro-Symbolic Systems 2640-3498 2505.19932 288 F. Kresse, E. Yu, C. Lampert, T.A. Henzinger, in:, 2nd International Conferenceon Neuro-Symbolic Systems, ML Research Press, 2025. Kresse, Fabian, et al. “Logic Gate Neural Networks Are Good for Verification.” 2nd International Conferenceon Neuro-Symbolic Systems, vol. 288, 26, ML Research Press, 2025. Kresse, Fabian, Emily Yu, Christoph Lampert, and Thomas A Henzinger. “Logic Gate Neural Networks Are Good for Verification.” In 2nd International Conferenceon Neuro-Symbolic Systems, Vol. 288. ML Research Press, 2025. Kresse F, Yu E, Lampert C, Henzinger TA. 2025. Logic gate neural networks are good for verification. 2nd International Conferenceon Neuro-Symbolic Systems. NeuS: International Conferenceon Neuro-Symbolic Systems, PMLR, vol. 288, 26. Kresse, F., Yu, E., Lampert, C., & Henzinger, T. A. (2025). Logic gate neural networks are good for verification. In 2nd International Conferenceon Neuro-Symbolic Systems (Vol. 288). Philadephia, PA, United States: ML Research Press. F. Kresse, E. Yu, C. Lampert, and T. A. Henzinger, “Logic gate neural networks are good for verification,” in 2nd International Conferenceon Neuro-Symbolic Systems, Philadephia, PA, United States, 2025, vol. 288. Kresse F, Yu E, Lampert C, Henzinger TA. Logic gate neural networks are good for verification. In: 2nd International Conferenceon Neuro-Symbolic Systems. Vol 288. ML Research Press; 2025. 202962025-09-07T22:01:34Z2025-09-09T08:12:44Z