Open-source alternatives to Audit

Cleverhans is an adversarial machine learning library and toolkit designed to generate adversarial examples, incorporate them into training loops, and benchmark the resilience of machine learning models. It provides a gradient-based attack framework for constructing both white-box and black-box attacks to identify model misclassifications. The project includes capabilities for model robustness benchmarking, allowing users to evaluate and verify how models resist evasion attacks and malicious input perturbations. It also facilitates adversarial training to increase a model's resistance to pert

Shannon is an integrated security platform designed for autonomous penetration testing, static and dynamic analysis, and automated vulnerability remediation within self-hosted, private infrastructure. It functions as a unified security suite that orchestrates the entire lifecycle of vulnerability management, from initial discovery and reachability prioritization to the generation and verification of code-level patches. The platform distinguishes itself through its agentic approach to security, deploying autonomous agents to execute both black-box and white-box exploits against running applica

Garak is a suite of tools for measuring AI reliability, scanning for vulnerabilities, and automating security assessments through adaptive probing. It functions as a generative AI vulnerability scanner and evaluation tool designed to identify security gaps, hallucinations, and failure modes in language models. The framework provides a toolkit for red-teaming and safety assessments, utilizing a structured system of probes and detectors to calculate failure rates. It specifically scans for risks such as data leakage and prompt injection by recording model responses to adversarial inputs. The p

Netron is a visualizer for neural network and machine learning models. It provides a graphical interface that renders model architectures as interactive node-link diagrams, allowing users to inspect internal layers, tensors, and metadata. By performing static analysis, the tool enables the examination of model definitions without executing the underlying machine learning code. The software distinguishes itself through a schema-driven parsing engine that translates diverse proprietary model formats into a unified internal graph structure. This approach ensures interoperability, allowing users

This project is no longer actively maintained. You are welcome to fork and continue its development on your own. Thank you for your interest and support.

Garak is an AI model evaluation tool and vulnerability scanner designed for red teaming large language models and auditing the security of retrieval-augmented generation pipelines. It identifies behavioral weaknesses, such as jailbreaks, hallucinations, and data leakage, by simulating adversarial attacks and executing automated testing vectors. The framework utilizes an adaptive probing loop where prompts can react to previous model behavior and be modified in flight via middleware. To ensure consistent analysis, it employs a provider-agnostic interface to interact with various model APIs and

NeMo-Guardrails is a toolkit for adding programmable safety constraints and dialogue boundaries to large language model conversational systems. It functions as security middleware that intercepts inputs and outputs to block prompt injections, jailbreaks, and sensitive data leaks, while providing a conversational dialogue manager to define structured interaction flows through configuration files. The framework includes a hallucination filter to screen model outputs for factual accuracy and a specialized modeling language for defining conversational flows and constraints. It provides capabiliti

Promptfoo is an evaluation framework designed for testing, benchmarking, and red-teaming language models and agentic workflows. It provides a unified environment to run prompts against multiple providers, allowing developers to systematically validate model outputs against objective assertions, semantic similarity metrics, and custom grading rubrics. The platform distinguishes itself through a provider-agnostic execution layer and a stateful orchestrator capable of simulating multi-turn conversations and complex tool-use trajectories. It includes a dedicated adversarial mutation pipeline that

A collection of real world AI/ML exploits for responsibly disclosed vulnerabilities

LLM Prompt Injection Detector

TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/

The Model Card Toolkit (MCT) streamlines and automates generation of Model Cards 1, machine learning documents that provide context and transparency into a model's development and performance. Integrating the MCT into your ML pipeline enables the sharing model metadata and metrics with…

Library for training machine learning models with privacy for training data

The Adversarial Robustness Toolbox (ART) is an open-source library that provides a unified framework for evaluating, defending, and certifying machine learning models against adversarial threats. It wraps models from any framework behind a common estimator interface, enabling composable pipelines for attack generation, defense application, robustness certification, and privacy auditing across evasion, poisoning, and extraction threats. The library distinguishes itself by covering the full adversarial ML security lifecycle within a single toolkit. It supports gradient-based adversarial example

A model-agnostic visual debugging tool for machine learning