| Vendor / publisher | Neural Network Verification project (Stanford and collaborators) | VeriVITAL, Vanderbilt University |
| Type | Open source · AI assurance & verification | Open source · AI assurance & verification |
| Official site | https://github.com/NeuralNetworkVerification/Marabou | https://verivital.github.io/nnv/ |
| Industries (cited page) | Aerospace & aviation | Aerospace & aviation |
| Frameworks named on cited source | None tagged | None tagged |
| Open source (OSI license on official repo) | Open source · BSD-3-Clause | Not an OSI-licensed official repo on this listing |
| Summary (from listing) | SMT-based neural-network verifier (Marabou 2.0). ONNX main format; also .nnet, TensorFlow and VNNLIB. pip install maraboupy (Python 3.8–3.11). Default: DeepPoly bound tightening and DeepSoI. Optional Gurobi, parallelism and Split-and-Conquer. ACAS Xu example. Research product. | MATLAB toolbox for set-based neural-network verification using Star sets and zonotopes. 10+ architectures and 48 layer types; ONNX and VNNLIB. Official aerospace domain and all 45 ACAS Xu networks. AFOSR, DARPA and NSF. |
| Last verified | 2026-10-14 | 2026-10-14 |
| Cited coverage (counts only) | No cited coverage cells in this bundle | No cited coverage cells in this bundle |
| Analyst assessments (counts only) | Analyst assessment: 1 NIST AI RMF function or subcategory — see which with Pro | Analyst assessment: 1 NIST AI RMF function or subcategory — see which with Pro |