What’s Vulnerable › Vulnerabilities

CVE-2026-73325: Fujitsu OneCompression < 1.2.1 Arbitrary Code Execution via torch.load Deserialization

• Severity: high (CVSS 7.8 v3.1)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 0.4% probability of exploitation in the next 30 days
• Public exploit or detection template: none known
• Published: 2026-08-12 · updated 2026-10-24
• Weakness: CWE-502

Description

Fujitsu Research's OneCompression library before 1.2.1 contains an unsafe deserialization vulnerability that allows attackers to execute arbitrary code by supplying a crafted model.pt checkpoint file, as QuantizedModelLoader.load_quantized_model_pt() unconditionally calls torch.load with weights_only=False, invoking Python's pickle machinery during deserialization. Attackers can embed malicious __reduce__ methods in a crafted model checkpoint to execute arbitrary Python code, including system commands, when the library loads the file from a caller-selected model directory.

Affected products

• Fujitsu Research OneCompression: before 1.2.1 — fixed in 1.2.1

How to fix

Upgrade to a fixed version: Fujitsu Research OneCompression 1.2.1. Check the vendor advisory for mitigations.

References

• https://github.com/FujitsuResearch/OneCompression/blob/main/SECURITY.md
• https://pypi.org/project/onecomp/
• https://pypi.org/project/onecomp/1.2.1/
• https://www.vulncheck.com/advisories/fujitsu-onecompression-arbitrary-code-execution-via-torch-load-deserialization

Get alerted when CVE-2026-73325 or the next vulnerability affects your stack