213 matches found
turboquant-monitoring-poc
TurboQuant x WhatAp Monitoring POC TurboQuanthttps://arxiv...
Deserialization of Untrusted Data
Overview megatron-core is a Megatron Core - a library for efficient and scalable training of transformer based models Affected versions of this package are vulnerable to Deserialization of Untrusted Data in the quantization configuration loading process. An attacker can execute arbitrary code,...
EUVD-2025-208974
NVIDIA Megatron LM contains a vulnerability in quantization configuration loading, which could allow remote code execution. A successful exploit of this vulnerability might lead to code execution, escalation of privileges, information disclosure, and data tampering...
CVE-2026-24141
NVIDIA Model Optimizer for Windows and Linux contains a vulnerability in the ONNX quantization feature, where a user could cause unsafe deserialization by providing a specially crafted input file. A successful exploit of this vulnerability might lead to code execution, escalation of privileges,...
CVE-2025-33247
NVIDIA Megatron LM contains a vulnerability in quantization configuration loading, which could allow remote code execution. A successful exploit of this vulnerability might lead to code execution, escalation of privileges, information disclosure, and data tampering...
CVE-2026-24141
CVE-2026-24141 affects NVIDIA Model Optimizer for Windows and Linux, where the ONNX quantization feature allows unsafe deserialization via a crafted input file. This can lead to code execution, escalation of privileges, data tampering, and information disclosure. NVIDIA states affected versions a...
CVE-2026-24141
NVIDIA Model Optimizer for Windows and Linux contains a vulnerability in the ONNX quantization feature, where a user could cause unsafe deserialization by providing a specially crafted input file. A successful exploit of this vulnerability might lead to code execution, escalation of privileges,...
CVE-2026-24141
NVIDIA Model Optimizer for Windows and Linux contains a vulnerability in the ONNX quantization feature, where a user could cause unsafe deserialization by providing a specially crafted input file. A successful exploit of this vulnerability might lead to code execution, escalation of privileges,...
CVE-2025-33247
NVIDIA Megatron LM contains a vulnerability in quantization configuration loading, which could allow remote code execution. A successful exploit of this vulnerability might lead to code execution, escalation of privileges, information disclosure, and data tampering...
CVE-2025-33247
NVIDIA Megatron LM contains a vulnerability in quantization configuration loading, which could allow remote code execution. A successful exploit of this vulnerability might lead to code execution, escalation of privileges, information disclosure, and data tampering...
CVE-2025-33247
NVIDIA Megatron LM is affected by CVE-2025-33247 due to a vulnerability in quantization configuration loading that could allow remote code execution. The security bulletin states this could lead to code execution, elevation of privileges, information disclosure, and data tampering. Affected produ...
CVE-2025-33247
NVIDIA Megatron LM contains a vulnerability in quantization configuration loading, which could allow remote code execution. A successful exploit of this vulnerability might lead to code execution, escalation of privileges, information disclosure, and data tampering...
CVE-2025-33247
NVIDIA Megatron LM contains a vulnerability in quantization configuration loading, which could allow remote code execution. A successful exploit of this vulnerability might lead to code execution, escalation of privileges, information disclosure, and data tampering...
PT-2026-27508
NVIDIA Model Optimizer for Windows and Linux contains a vulnerability in the ONNX quantization feature, where a user could cause unsafe deserialization by providing a specially crafted input file. A successful exploit of this vulnerability might lead to code execution, escalation of privileges,...
CVE-2026-24141: Deserialization of Untrusted Data
NVIDIA Model Optimizer for Windows and Linux contains a vulnerability in the ONNX quantization feature, where a user could cause unsafe deserialization by providing a specially crafted input file. A successful exploit of this vulnerability might lead to code execution, escalation of privileges,...
NVIDIA Model Optimizer 代码问题漏洞
NVIDIA Model Optimizer is a tool component developed by NVIDIA Corporation that optimizes the performance of deep learning models and improves inference efficiency. NVIDIA Model Optimizer has a code vulnerability, which stems from an insecure deserialization issue in the ONNX quantization functio...
Security Bulletin: NVIDIA Megatron LM - March 2026
NVIDIA has released a software update for NVIDIA® Megatron LM. To protect your system, clone or update this software to version 0.15.3 or later from NVIDIA/Megatron-LM on GitHub. Go to NVIDIA Product Security. Details The following table summarizes the potential vulnerabilities that this security...
PT-2026-27505
NVIDIA Megatron LM contains a vulnerability in quantization configuration loading, which could allow remote code execution. A successful exploit of this vulnerability might lead to code execution, escalation of privileges, information disclosure, and data tampering...
CVE-2025-69693
Out-of-bounds read in FFmpeg 8.0 and 8.0.1 RV60 video decoder libavcodec/rv60dec.c. The quantization parameter qp validation at line 2267 only checks the lower bound qp 0 but is missing upper bound validation. The qp value can reach 65 base value 63 from 6-bit frame header + offset +2 from...
ffmpeg 安全漏洞
FFmpeg is a Rust library developed by a single developer. Versions 8.0 and 8.0.1 of FFMPEG contain security vulnerabilities, which stem from an oversight in the validation of quantization parameters. These vulnerabilities may lead to out-of-bounds reads, memory leaks, or system crashes...