PyRIT

Risk analyzer

Automates security risk identification and red teaming in generative AI systems

The Python Risk Identification Tool for generative AI (PyRIT) is an open access automation framework to empower security professionals and machine learning engineers to proactively find risks in their generative AI systems.

GitHub

2k stars
27 watching
364 forks
Language: Python
last commit: 6 days ago
Linked from 1 awesome list

ai-red-teamgenerative-aired-team-toolsresponsible-ai

Backlinks from these awesome lists:

Related projects:

Repository Description Stars
ensta-u2is-ai/torch-uncertainty Provides tools and methods to quantify uncertainty in deep learning models and improve their reliability 304
claudiugeorgiu/riskindroid An Android app risk analysis tool using machine learning and reverse engineering to evaluate permission usage and risks. 136
endgameinc/rta A framework of python scripts designed to test detection capabilities against malicious tradecraft modeled after MITRE ATT&CK tactics. 1,050
embodiedgpt/embodiedgpt_pytorch A PyTorch-based toolkit for creating customized multimedia datasets and handling heterogeneous data for training AI models. 340
orobix/visual-feature-attribution-using-wasserstein-gans-pytorch A PyTorch implementation of a feature attribution technique using Wasserstein Generative Adversarial Networks for anomaly detection in medical images. 93
arm-doe/pyart An interactive toolkit for working with weather radar data using Python and atmospheric radar algorithms 516
apger/sa-rba A Splunk add-on that provides risk-based alerting capabilities using Python and integrates with Splunk Enterprise Security 45
ai-secure/decodingtrust An assessment tool for evaluating trustworthiness in GPT models across various aspects such as toxicity, bias, robustness, and fairness. 259
python-security/pyt A tool that analyzes Python web applications for potential security vulnerabilities 2,176
tripwire/tardis An intelligence platform for threat analysis and incident response 121
ctallec/pyvarinf A Python package facilitating Bayesian Deep Learning methods with Variational Inference for PyTorch 359
project-dc/pygeneses A PyTorch-based framework for training and studying artificial species in bio-inspired environments 72
jphall663/gai_risk_management Resources to help organizations manage risks associated with Generative AI systems 10
someengineering/fixinventory Tools to identify and remove critical risks in cloud infrastructure accounts by analyzing metadata from APIs of various cloud services 1,608
stratosphereips/manati A tool to assist threat analysts in discovering new security problems using machine learning 112