Lucene search
K

The vulnerability of BERT, the language model encoder for NVIDIA NeMo’s complex platform for training and applying neural networks in speech processing and natural language processing, allows a perpetrator to execute arbitrary code, gain unauthorized access to protected information, or replace data.

🗓️ 01 Dec 2025 00:00:00Reported by FSTEC of Russia — Information Security Threat DatabaseType 
bdu_fstec
 bdu_fstec
🔗 bdu.fstec.ru👁 1 Views

BERT encoder in NVIDIA NeMo platform has code generation flaws enabling arbitrary code execution and data access or substitution.

Related
Detection
Refs

Data

Build on a solid foundation with Vulners data

We provide the essential building blocks for cybersecurity solutions with comprehensive, structured, and constantly updated vulnerability and exploits data

Api

Power your application with Vulners API

The Vulners REST API offers reliable, high-performance access to vulnerability intelligence, with 99.9% SLA uptime and CDN-backed data delivery for seamless global access

App

Assess and manage vulnerabilities with Vulners tools

Built on top of Vulners' database and SDK, end-user solutions give security professionals and developers lightweight and powerful tools for vulnerability remediation

01 Dec 2025 00:00Current
6.3Medium risk
Vulners AI Score6.3
CVSS 26.8
CVSS 37.8
EPSS0.00275
1