Browse / Unsafe Model Loading and Supply Chain / CVE-2026-31238
Ludwig framework is vulnerable to insecure deserialization in its model serving component
- Class
- Unsafe Model Loading and Supply Chain (filed by a model that read the advisory)
- Technique
- Unsafe deserialisation
- Affected
- ludwig (PyPI)
- CVSS
- CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
- EPSS
- 0.5% chance of exploitation in 30 days
How it works, in short
The model server loads weight files with unrestricted torch.load, so a crafted checkpoint executes arbitrary Python objects when served. (Our summary, written by a model. The source text is below.)
Details
The Ludwig framework thru 0.10.4 is vulnerable to insecure deserialization (CWE-502) in its model serving component. When starting a model server with the ludwig serve command, the framework loads model weight files using torch.load() without enabling the security-restrictive weights_only=True parameter. This default behavior allows the deserialization of arbitrary Python objects via the pickle module. An attacker can exploit this by providing a maliciously crafted PyTorch model file, leading to arbitrary code execution on the system hosting the Ludwig model server.
References
- https://nvd.nist.gov/vuln/detail/CVE-2026-31238
- https://github.com/ludwig-ai/ludwig
- https://github.com/pypa/advisory-database/tree/main/vulns/ludwig/PYSEC-2026-405.yaml
- https://pypi.org/project/ludwig
- https://www.notion.so/CVE-2026-31238-35d1e1393188819ea77ee98ca85a2878
Source: GitHub Advisory Database, used under CC BY 4.0.