Code execution via malicious model deserialization
Published Dec 16, 2025 · Updated Dec 16, 2025
Deserialization in NVIDIA NeMo Framework before 2.5.3 allows local users to execute code by inducing a user to load a malicious model file. NVIDIA has not disclosed the model-loading entry point or the improper control that processes attacker-supplied content. Successful exploitation runs code with the loader process privileges and can alter data, elevate privileges, or crash the process; user interaction is required.
Summary
What happened
Deserialization in NVIDIA NeMo Framework before 2.5.3 allows local users to execute code by inducing a user to load a malicious model file. NVIDIA has not disclosed the model-loading entry point or the improper control that processes attacker-supplied content. Successful exploitation runs code with the loader process privileges and can alter data, elevate privileges, or crash the process; user interaction is required.
The record
- CVE
- CVE-2025-33212
- Published
- Dec 16, 2025
- Updated
- Dec 16, 2025
- Vendor
- DPDK Project
- Product
- NeMo Framework
- Classifications
- CWE-502, T1204.002
- Attack vector
- local
- Privileges
- authenticated
Timeline
How it unfolded
- Dec 16, 2025CVE publishedPublication date reported by the CVE source.
- Dec 16, 2025Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=All versions prior to 2.5.3
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Public exploit references
No public exploit references are available in this record.
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo