Steal-ML
Model extractor
A tool for extracting machine learning models from cloud-based services using prediction APIs
Model extraction attacks on Machine-Learning-as-a-Service platforms.
344 stars
18 watching
96 forks
Language: Python
last commit: almost 6 years agoRelated projects:
| Repository | Description | Stars |
|---|---|---|
| A tool to extract memorized content from large language models like GPT-2 by analyzing their training data | 179 | |
| Evaluates and compares the performance of multimodal large language models on various tasks | 56 | |
| A Python library for scalable machine learning using Dask alongside popular ML libraries | 907 | |
| Teaching software developers how to build transparent and explainable machine learning models using Python | 673 | |
| This implementation allows an attacker to directly obtain user data from federated learning gradient updates by modifying the shared model architecture. | 23 | |
| Recovering Private Text in Federated Learning of Language Models by attacking language models to extract private client data | 57 | |
| An implementation of model poisoning attacks in federated learning | 146 | |
| A collection of sample applications demonstrating the use of Amazon Machine Learning API for various machine learning tasks | 873 | |
| A framework to help security analysts understand and prepare for adversarial machine learning attacks on AI systems | 1,056 | |
| Measures the performance of deep learning models in various deployment scenarios. | 1,256 | |
| Evaluates and visualizes the performance of machine learning models. | 1,258 | |
| A FastAPI-based framework for serving machine learning models in production-ready applications | 412 | |
| Analyzes and dumps memory to extract sensitive information from running processes | 582 | |
| Reconnaissance tool that gathers information about a Cloudflare-protected target to discover its server location using misconfigured DNS and old database records. | 2,251 | |
| Tools for building machine learning solutions on satellite imagery | 81 |