CVE-2026-31238
CriticalSummary
The Ludwig framework up to version 0.10.4 is vulnerable to insecure deserialization in its model serving component. When starting a model server with the ludwig serve command, the framework loads model weight files without enabling the security-restrictive weights_only=True parameter, allowing the deserialization of arbitrary Python objects.
Risk Assessment
An attacker can exploit this vulnerability by providing a maliciously crafted PyTorch model file, leading to arbitrary code execution on the system hosting the Ludwig model server. This poses a significant security risk to the system.
Recommendation
It is recommended to update the Ludwig framework to the latest version and enable the weights_only=True parameter when loading model weight files to minimize the risk of unauthorized deserialization.
Original NVD description (English source)
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.