Score: 0

Logic Gate Neural Networks are Good for Verification

Published: May 26, 2025 | arXiv ID: 2505.19932v1

By: Fabian Kresse , Emily Yu , Christoph H. Lampert and more

Potential Business Impact:

Makes AI easier to check for mistakes.

Business Areas:
Field-Programmable Gate Array (FPGA) Hardware

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.

Country of Origin
🇦🇹 Austria

Page Count
15 pages

Category
Computer Science:
Machine Learning (CS)