VulnerabilityPublished 9 Dec 2025

CVE-2025-33213: NVIDIA Merlin Transformers4Rec · Deserialization of Untrusted Data

Affects NVIDIA Merlin Transformers4RecSource CVE Database V5

Not known to be exploited · CVSS 8.8 High.

Data as of 26 Oct 2026, 17:16 UTC

CVSS 3.1 base score

8.8High

How severe the flaw is on the 0–10 CVSS scale.

EPSS: 0.6% chance of exploitation in 30 days – higher than 51% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.

CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

Attack Vector: Network
Attack Complexity: Low
Privileges Required: None
User Interaction: Required
Scope: Unchanged
Confidentiality: High
Integrity: High
Availability: High

Bold values are the worst case: easiest to exploit or largest impact.

Attack Vector: Network: The vulnerable component is bound to the network stack and the set of possible attackers extends beyond the other options listed, up to and including the entire Internet. Such a vulnerability is often termed 'remotely exploitable' and can be thought of as an attack being exploitable at the protocol level one or more network hops away (e.g., across one or more routers).
Attack Complexity: Low: Specialized access conditions or extenuating circumstances do not exist. An attacker can expect repeatable success against the vulnerable component.
Privileges Required: None: The attacker is unauthorized prior to attack, and therefore does not require any access to settings or files to carry out an attack.
User Interaction: Required: Successful exploitation of this vulnerability requires a user to take some action before the vulnerability can be exploited.
Scope: Unchanged: An exploited vulnerability can only affect resources managed by the same security authority. In this case, the vulnerable component and the impacted component are either the same, or both are managed by the same security authority.
Confidentiality: High: There is total loss of confidentiality, resulting in all resources within the impacted component being divulged to the attacker. Alternatively, access to only some restricted information is obtained, but the disclosed information presents a direct, serious impact.
Integrity: High: There is a total loss of integrity, or a complete loss of protection. For example, the attacker is able to modify any/all files protected by the impacted component. Alternatively, only some files can be modified, but malicious modification would present a direct, serious consequence to the impacted component.
Availability: High: There is total loss of availability, resulting in the attacker being able to fully deny access to resources in the impacted component; this loss is either sustained (while the attacker continues to deliver the attack) or persistent (the condition persists even after the attack has completed). Alternatively, the attacker has the ability to deny some availability, but the loss of availability presents a direct, serious consequence to the impacted component (e.g., the attacker cannot disrupt existing connections, but can prevent new connections; the attacker can repeatedly exploit a vulnerability that, in each instance of a successful attack, leaks a only small amount of memory, but after repeated exploitation causes a service to become completely unavailable).

Definitions: FIRST CVSS v3.1 specification.

Exploitation evidence

Disclosed: evidence found.
CVE published 9 Dec 2025
Detectable: no evidence on record.
No public nuclei template indexed
Weaponised: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 26 Oct 2026.

Disclosed: The CVE record is public on cve.org. Its publication is t = 0.
Detectable: A public nuclei template can find exposed instances, for defenders and attackers alike.
Weaponised: Public exploit code exists in Metasploit or Exploit-DB, or CISA SSVC or the CVSS exploit maturity reports a public proof of concept.
Exploited in the wild: CISA KEV lists it, CISA SSVC rates exploitation active, or a source reports attacks.
Observed by OffSeq Mirage: OffSeq Mirage honeypot sensors recorded attack traffic for this CVE, or found exposed hosts without attack traffic.

Moments are spaced evenly, not to scale; a dashed line marks a gap of six months or more. Deltas count from t = 0. Sources that give only a date (CISA KEV, Exploit-DB, or a time of exactly 00:00Z) read “same day” rather than hours. Metasploit modules carry the flaw’s disclosure date, not their release date, and nuclei templates carry no date, so both appear above but not on the timeline.

What to do

AI-suggested

To mitigate this vulnerability, European organizations should immediately update Merlin Transformers4Rec to a version that includes the commit 876f19e or later, which addresses the deserialization flaw. Until patches are applied, restrict network access to the Trainer component using firewalls or network segmentation to limit exposure to untrusted sources. Implement strict input validation and sanitization to prevent malicious serialized data from being processed. Employ application-level controls such as sandboxing or running the Trainer with least privilege to reduce the impact of potential exploitation. Monitor logs and network traffic for unusual activity indicative of exploitation attempts. Additionally, review and harden AI/ML pipeline security policies, including secure coding practices for handling serialized data. Regularly audit and update dependencies to minimize exposure to similar vulnerabilities.

Description

CVE-2025-33213 is a high-severity vulnerability in NVIDIA Merlin Transformers4Rec's Trainer component on Linux, involving deserialization of untrusted data (CWE-502). Exploiting this flaw could allow remote attackers to execute arbitrary code, cause denial of service, disclose sensitive information, or tamper with data. The vulnerability affects all versions prior to a specific commit (876f19e) and requires user interaction but no privileges. Although no known exploits are currently in the wild, the CVSS score of 8.8 indicates significant risk. European organizations using Merlin Transformers4Rec in AI/ML workflows should prioritize patching and implement strict input validation and network segmentation. Countries with strong AI research and industries relying on NVIDIA AI tools, such as Germany, France, and the UK, are most likely to be impacted. Immediate mitigation steps include updating to the fixed version, restricting Trainer component access, and monitoring for suspicious activity.

Impact

For European organizations, the impact of CVE-2025-33213 is significant due to the increasing adoption of AI and machine learning frameworks like NVIDIA Merlin Transformers4Rec in sectors such as e-commerce, finance, telecommunications, and research institutions. Successful exploitation could lead to unauthorized control over AI training environments, resulting in corrupted or manipulated recommendation models, leakage of proprietary or personal data, and service disruptions. This can undermine trust in AI systems, cause financial losses, and violate data protection regulations such as GDPR. Additionally, denial of service attacks could interrupt critical AI workflows, affecting business continuity. Organizations relying on NVIDIA AI tools in cloud or on-premises environments are at risk, especially if the Trainer component is exposed to untrusted inputs or accessible over the network without adequate controls.

Summary

CVE-2025-33213 is a deserialization vulnerability (CWE-502) found in the Trainer component of NVIDIA Merlin Transformers4Rec, a Linux-based AI recommendation system framework. The flaw arises from improper handling of untrusted serialized data, which can be manipulated by an attacker to execute arbitrary code within the Trainer process. This vulnerability can also lead to denial of service by crashing the Trainer, unauthorized disclosure of sensitive information processed during training, and tampering with training data or model parameters. The vulnerability affects all versions of Merlin Transformers4Rec that do not include the commit identified as 876f19e, which presumably contains the patch. The CVSS v3.1 base score is 8.8, reflecting high severity with network attack vector (AV:N), low attack complexity (AC:L), no privileges required (PR:N), but requiring user interaction (UI:R). The scope is unchanged (S:U), and the impact on confidentiality, integrity, and availability is high (C:H/I:H/A:H). No known exploits have been reported in the wild yet, but the potential for remote code execution makes this a critical concern for deployments. The vulnerability is particularly relevant for organizations leveraging Merlin Transformers4Rec for AI-driven recommendation systems, as exploitation could compromise the integrity and confidentiality of AI models and data pipelines.

CWE-502Deserialization of Untrusted Data (opens in a new tab)
Base weaknessLikelihood of exploit: MediumCWE Top 25 (2025): #15OWASP Top 10 A08:2025: Software or Data Integrity Failures (opens in a new tab)
The product deserializes untrusted data without sufficiently ensuring that the resulting data will be valid.
Architecture and Design · Implementation
If available, use the signing/sealing features of the programming language to assure that deserialized data has not been tainted. For example, a hash-based message authentication code (HMAC) could be used to ensure that data has not been modified.
Implementation
When deserializing data, populate a new object rather than just deserializing. The result is that the data flows through safe input validation and that the functions are safe.
Implementation
Explicitly define a final object() to prevent deserialization.
OWASP Cheat Sheets
Abuse Case (opens in a new tab)
Deserialization (opens in a new tab)
XML Security (opens in a new tab)
XML External Entity Prevention (opens in a new tab)
Software Supply Chain Security (opens in a new tab)
OWASP ASVS 4.0.3
V1.5.2 (opens in a new tab)
V5.5.3 (opens in a new tab)
V5.5.1 (opens in a new tab)
Attack patterns
Object Injection (opens in a new tab)
From MITRE CWE, MITRE CAPEC and OWASP (Top 10, OpenCRE).

References

Community reviews

Loading reviews…

Exploitation evidence

What to do

Description

AI analysisMachine-generated, updated 16 Dec 2025, 21:12 UTC

WeaknessesCWE-502

Technical details

References

Community reviews

Related threats