CVE-2026-31218: optimate insecure deserialization in _load_model() via torch.load()

Summary

The _load_model() function in the neural_magic_training.py script of the optimate project, at commit a6d302f912b481c94370811af6b11402f51d377f (2024-07-21), is affected by insecure deserialization (CWE-502). It calls torch.load() on a state_dict.pt file without setting weights_only=True, so arbitrary Python objects can be deserialized through the Pickle module. A remote attacker who supplies a crafted state_dict.pt in a directory passed via the --model argument can execute arbitrary code on the victim's system during deserialization.

Mitigation

The source does not state a fix yet. Check the original advisory for updates.

Related items

• InfoCVE-2026-123357: GROBID command execution through crafted PDF filename in Linux conversionSimilar attack · NVD/CVE Database
• MediumShai-Hulud Descendant Surfaces in Malicious Ruby Gem That Steals Credentials and Poisons AI ToolsSimilar attack · Socket Blog
• MediumCPython flaw exposes AI inference servers to sandbox escape attacksSimilar attack · CSO Online
• HighCVE-2026-88981: Kubeflow Pipelines enables users to build and deploy portable, scalable machine learning workflows. Prior to 2.18.0…Similar attack · NVD/CVE Database
• MediumBinance heist is stark example of AI governance gaps and basic security failuresSimilar attack · CSO Online