AI Assurance Directory

AI assurance & verification

nnenum

Evidence strength: Moderate 0 cited · 1 literature · 1 analyst How this is scored

Python 3.9+ neural-network verifier (pip install .; nnenum 1.0.1, GPL-3.0-or-later) for ReLU networks. Combines zonotopes with star sets, uses the ImageStar trick through ONNX Runtime, and ships ACAS Xu ONNX/vnnlib examples. VNN-COMP 2020: only tool to verify all ACAS-Xu benchmarks.

Certification evidence

0 cited mappings · 1 cited-literature paper · 1 analyst assessment across 2 frameworks. Counts are public. Requirement labels and quotes stay on Pro.

Cited literature: 1 DO-178C / related aerospace guidance requirement — see which with Pro

Analyst assessment: 1 NIST AI RMF function or subcategory — see which with Pro

Certification relevance. peer-reviewed or agency literature maps it to DO-178C / related aerospace guidance (1 requirement).

Cited literature: nnenum: Verification of ReLU Neural Networks with Optimized Abstraction Refinement (NASA Formal Methods 2021 (NFM 2021), 2021) — a named DO-178C / related aerospace guidance requirement.

Paper or report · The quoted wording is Pro.

Listing detail and source evidence (Pro)

Included on Pro, Team and Enterprise. Public summaries, tags and official links on this page stay free.

See plans · Sign in

Cited literature and analyst assessments (Pro)

Included on Pro, Team and Enterprise. Public summaries, tags and official links on this page stay free.

See plans · Sign in

Procurement evidence pack (Pro) — print cited mappings and analyst notes. The print view is not on this page.

Vendor / publisher
Stanley Bak
Type
Open source
Open source
Open source · GPL-3.0-or-later on the official repository https://github.com/stanleybak/nnenum. Badge is used only when that repo shows an OSI-approved license.
Official site
https://github.com/stanleybak/nnenum
Industries
Frameworks named on cited source
None tagged. The cited pages do not name a framework we cover.
Last verified

Listing is not an endorsement, certification or recommendation. Capabilities, availability and framework support can change. Confirm with the vendor and the relevant authority. See the disclaimer.