Adopt Model security Defense
ModelScan
ModelScan is an open-source Protect AI scanner that inspects ML model files (Pickle, H5, SavedModel, Keras and others) for unsafe embedded code without loading them. It is aimed at teams that consume third-party or pipeline-produced models.
Mature and widely used; a sensible default for most teams.
Facts
- Repository
- protectai/modelscan
- Homepage
- github.com
- Listed via
- Curated
- First seen
- 2026-11-08
- License
- Apache-2.0
- Stars
- 793
- Last commit
- 2026-09-28
- Latest release
- v0.8.8 · 2026-02-18
- Checked
- 2026-11-10
Techniques
Listing is not endorsement. Summaries and notes are AI-assisted and reviewed; repository facts refresh automatically.