saffron

Saffron-1: Escalado de Inferencia para la Garantía de Seguridad de LLM 📖 Artículo 🛠️ Dependencias El código fue probado con las siguientes dependencias: Python 3.12.3 CUDA 12.2 typingextensions==4.14.0 numpy==2.2.6 torch==2.5.1 huggingfacehub==0.30.2 accelerate==1.1.1 datasets==3.1.0...

alibi-detect

Alibi Detect is a source-available Python library focused on outlier , adversarial and drift detection. The package aims to cover both online and offline detectors for tabular data, text, images and time series. Both TensorFlow and PyTorch backends are supported for drift detection. Documentation...

cleverhans

CleverHans latest release: v4.0.0 This repository contains the source code for CleverHans, a Python library to benchmark machine learning systems' vulnerability to adversarial examples. You can learn more about such vulnerabilities on the accompanying blog. The CleverHans library is under continu...

foolbox

home: true heroImage: /logo.png heroText: Foolbox tagline: "Foolbox：在 PyTorch、TensorFlow 和 JAX 中快速发起对抗攻击，以基准测试机器学习模型的鲁棒性" actionText: 开始使用 → actionLink: /guide/ features: title: 原生性能 details: Foolbox 3 基于 EagerPy 构建，可原生运行于 PyTorch、TensorFlow 和 JAX 中。 title: 最先进的攻击方法 details: Foolbox...

netsentryx

NetSentryx PRO 🛡️ Motor de Detección de Amenazas y Observabilidad de Red en Tiempo Real de Alto Rendimiento Impulsado por IA NetSentryx PRO es una plataforma de inteligencia de amenazas y monitoreo de red basada en eventos de próxima generación. Combinando firmas basadas en reglas con un...

LMDeploy vulnerable to arbitrary code execution via eval() of untrusted quant_dtype in model config loading

Summarylmdeploy = latest contains a code injection vulnerability in lmdeploy/pytorch/config.py line 620 that allows an attacker to execute arbitrary Python code by publishing a malicious HuggingFace model with a crafted quantizationconfig.quantdtype value. When a user loads the model with lmdeplo...

LMDeploy has Remote Code Execution by Pickle Deserialization via handle_zmq_recv in lmdeploy/lmdeploy/pytorch/disagg/conn/engine_conn.py

SummaryLMDeploy's PyTorch DistServe/PD-disaggregation control plane usedrecvpyobj to deserialize messages received through a ZeroMQ PULLsocket. PyZMQ implements recvpyobj using Python pickledeserialization, which can execute arbitrary code while reconstructingan object.The peer address used by th...

Picklescan is vulnerable to RCE through missing detection when calling numpy.f2py.crackfortran.myeval

SummaryPicklescan uses numpy.f2py.crackfortran.myeval, which is a function in numpy to execute remote pickle files. DetailsThe attack payload executes in the following steps:- First, the attacker crafts the payload by calling the numpy.f2py.crackfortran.myeval function in its reduce method- Then,...

Picklescan missing detection when calling pytorch function torch.jit.unsupported_tensor_ops.execWrapper

SummaryUsing torch.jit.unsupportedtensorops.execWrapper function, which is a pytorch library function to execute remote pickle file. DetailsThe attack payload executes in the following steps:First, the attacker craft the payload by calling to torch.jit.unsupportedtensorops.execWrapper function in...

cve-2025-32434-poc

CVE-2025-32434 Descripción Detalles Técnicos El punto de entrada de la vulnerabilidad es load en torch/serialization.py cuando la protección weightsonly está habilitada: cargar un archivo tar llamaría a estas funciones en cadena: 1. load: torch/serialization.py:1117 2. loadlegacy:...

CVE-2025-32434

CVE-2025-32434: PyTorch RCE Vulnerability - PoC What is CVE-2025-32434? CVE-2025-32434 is a critical Remote Code Execution RCE vulnerability in PyTorch, a widely used Python library for deep learning and neural networks. The Core Problem The vulnerability exists in the torch.load function, even...

fickling

Fickling Fickling 是一个用于 Python pickle 对象序列化的反编译器、静态分析器和字节码重写器。你可以使用 fickling 来检测、分析、逆向工程，甚至创建恶意的 pickle 或基于 pickle 的文件，包括 PyTorch 文件。 Fickling 既可以作为 Python 库 使用，也可以作为 CLI 使用。 安装 保护 AI/ML 环境 通用恶意文件检测 高级用法 跟踪 pickle 执行 Pickle 代码注入 Pickle 反编译 PyTorch 多格式文件（polyglots） 更多信息 联系方式 安装 Fickling 已在 Python...

EXPLOIT-CVE-2024-7804

CVE-2024-7804 — PyTorch Distributed RPC Unsafe Deserialization RCE Self-contained lab + exploit for CVE-2024-7804 : remote code execution in PyTorch's distributed RPC framework torch.distributed.rpc through unsafe deserialization of untrusted data CWE-502. Affected: torch Note: this advisory was...

Occ

Prohibited Items Segmentation via Occlusion-aware Bilayer Modeling ICME 2025 Official PyTorch Implementation of Prohibited Items Segmentation via Occlusion-aware Bilayer Modeling. Paper link: IEEE, Arxiv. Get Started Dependencies Code is successfully tested on Linux with Pytorch 2.1.2 and CUDA...

CVE-2024-5452

CVE-2024-5452 01. Descripción general de RCE y pytorch-lightning 1 Descripción general de RCE y pytorch-lightning RCE Remote Code Execution, ejecución remota de código es una vulnerabilidad que permite a un atacante ejecutar código arbitrario de forma remota dentro de un sistema o aplicación, y...

CLIPGuard

CLIPGuard Installation 1. Create Virtual Environment Recommended python -m venv clipguardenv source clipguardenv/bin/activate 2. Install PyTorch CUDA Example pip install torch torchvision --index-url https://download.pytorch.org/whl/cu121 For CPU: pip install torch torchvision 3. Install...

CVE-2025-32434-exploit

Resumen Este exploit demuestra una vulnerabilidad crítica de ejecución remota de código CVE-2025-32434 en versiones de PyTorch /tmp/whoami" Test the exploit loads the model to verify RCE python3 exploit.py -c "id" -t Advanced exploit variant with alternative bypass python3 exploit.py --advanced -...

CVE-2025-50461

CVE-2025-50461: Ejecución Remota de Código mediante Deserialización Insegura de Modelos en Verl Estado: RESERVADO Este ID de CVE ha sido asignado pero aún no está publicado en la lista oficial de CVE. Existe una vulnerabilidad de deserialización en Volcengine's verl 3.0.0, específicamente en el...

CVE-2023-43654

CVE-2023-43654 ShellTorch es una cadena de 3 vulnerabilidades críticas en PyTorch TorchServe, el servidor de inferencia predeterminado de PyTorch. Este es un POC de extremo a extremo para una vulnerabilidad de SSRF que conduce a ejecución remota de código arbitrario desde la red 1. Ejecuta...

Agentic-CLIP-Benchmark

Agentic-CLIP-Benchmark: Zero-Shot Evaluation on CIFAR-10 -green.svg This project implements a robust, automated pipeline for evaluating OpenAI's CLIP ViT-B/32 model on the full CIFAR-10 test set 10,000 images. Developed using an AI Native workflow Trae IDE , it achieves a high-precision zero-shot...