🧠 LLMFuzzer - Fuzzing Framework for Large Language Models 🧠 LLMFuzzer is the first open-source fuzzing framework specifically designed for Large Language Models (LLMs), especially for their integrations in applications via LLM APIs. 🚀💥

Securing LLM's Against Top 10 OWASP Large Language Model Vulnerabilities 2024

OllaDeck is a purple technology stack for Generative AI (text modality) cybersecurity. It provides a comprehensive set of tools for both blue team and red team operations in the context of text-based generative AI.

Working Memory Attack on LLMs

An intentionally vulnerable AI chatbot to learn and practice AI Security.

A high-performance string formatter written in Rust. This project detects and blocks LLM prompt injection and jailbreak attacks. It also features a customizable rule-based system and defends against obfuscated prompt attacks.

AI Red Team & Blue Team Tips & Tricks!

[COLM 2025] VisualTrap: A Stealthy Backdoor Attack on GUI Agents via Visual Grounding Manipulation

AiShields is an open-source Artificial Intelligence Data Input and Output Sanitizer

A series of serverless functions/resources (and Terraform) for consuming language model inputs and outputs to S3, enriching the data via sentiment analysis and topic modelling, loading to DynamoDB and subsequently monitoring for configurable deviation within the latent vector space.

The Citadel is not just a training platform; it is a battleground. As AI systems integrate deeper into our critical infrastructure, the attack surface expands exponentially. This application is a purpose-built LLM Pentesting Environment designed to simulate real-world threats against Large Language Models.

Protect your AI interactions

A powerful, community-curated toolkit to attack, evaluate, defend, and monitor Large Language Models (LLMs) — covering everything from prompt injection to jailbreak detection.

Master's thesis repo focused on evaluating generational improvements on LLMs security.

Promptsploit is a tool that help you check you LLM tools against security vulnerabilities.

LMTWT is AI security testing framework for evaluating LLM prompt injection vulnerabilities

This repository contains the implementation and benchmarking framework for AI Guardrails, specifically focusing on hallucination detection in Large Language Models (LLMs). The project was developed for PyCon Taiwan 2025 presentation on AI safety and reliability.