MediumVulnerabilityLLM-specific

CVE-2025-4701: VITA-MLLM Freeze-Omni deserialization via torch.load path argument

Source: NVD(opens in a new tab)
Identifier: CVE-2025-4701
Published: May 15, 2025
Record updated: October 9, 2026

Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 0.2%

Summary

CVE-2025-4701 affects VITA-MLLM Freeze-Omni up to 20250421. A flaw in the torch.load function in models/utils.py lets manipulation of the path argument lead to deserialization. The attack can be launched on the local host, and VulDB rates it CVSS 4.0 4.8 MEDIUM (AV:L/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N), with NIST assessment not yet provided.

Mitigation

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

Details

Scores and exploitation

CVSS score: 5.3(medium)
EPSS: 0.2%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on November 4, 2026.

Weaknesses and techniques

Weakness (CWE): CWE-20
CWE-502
Attack pattern (CAPEC): CAPEC-586

Classification

Attack type: Other
Attack sophistication: Moderate
AI component targeted: Framework
Impact: Confidentiality,
Integrity,
Availability
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative. The source gives this advisory a description and no title, so the title above is a headline generated from the source text.

Original source: https://nvd.nist.gov/vuln/detail/CVE-2025-4701

First tracked: February 15, 2026 at 08:53 PM ET, from NVD/CVE Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 90% (self-assessed)

Summary

Mitigation

Related items