c0de3

llm-adaptive-attacks

Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [arXiv, Apr 2024]

CVE-2024-29943

A Pwn2Own SpiderMonkey JIT Bug: From Integer Range Inconsistency to Bound Check Elimination then RCE

semantic-kernel

Integrate cutting-edge LLM technology quickly and easily into your apps

ReNeLLM

The official implementation of our NAACL 2024 paper "A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily".

LLM4Decompile

Reverse Engineering: Decompiling Binary Code with Large Language Models

sparse_autoencoder

Data-governance

This project is an open source AI data governance framework designed to assist organizations in managing and maintaining their data assets to ensure data quality, consistency, and security.

CAA

Steering Llama 2 with Contrastive Activation Addition

DeepSeek-Coder

DeepSeek Coder: Let the Code Write Itself

PoisonPrompt

Code for paper: PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models, IEEE ICASSP 2024. Demo:http://124.220.228.133:11003

LabASPIRE

Contains several related topics about the area under research.

llama3-jailbreak

A trivial programmatic Llama 3 jailbreak. Sorry Zuck!

ps-fuzz

Make your GenAI Apps Safe & Secure :rocket: Test & harden your system prompt

PromptFuzz

PromtFuzz is an automated tool that generates high-quality fuzz drivers for libraries via a fuzz loop constructed on mutating LLMs' prompts.

xTuring

Build, customize and control you own LLMs. From data pre-processing to fine-tuning, xTuring provides an easy way to personalize open-source LLMs. Join our discord community: https://discord.gg/TgHXuSJEk6

RedPajama-Data

The RedPajama-Data repository contains code for preparing large datasets for training large language models.

awesome-ml-privacy-attacks

An awesome list of papers on privacy attacks against machine learning

ai-exploits

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

ollama

Get up and running with Llama 2, Mistral, Gemma, and other large language models.

PyRIT-Redteam

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.

certified-llm-safety

carving

Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives

pal

PAL: Proxy-Guided Black-Box Attack on Large Language Models

LLMFuzzer

🧠 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. 🚀💥

AutoPoison

The official repository of the paper "On the Exploitability of Instruction Tuning".

Deepfake_detection_using_deep_learning

This projects aims in detection of video deepfakes using deep learning techniques like RestNext and LSTM. We have achived deepfake detection by using transfer learning where the pretrained RestNext CNN is used to obtain a feature vector, further the LSTM layer is trained using the features. For more details follow the documentaion.

ExtractGPT

Attribute Value Extraction using Large Language Models

Local-LLM-Server

quick way to build a private large language model server and provide OpenAI-compatible interfaces | 快速搭建私有大语言模型（LLM）服务，提供OpenAI兼容接口

caldera

Automated Adversary Emulation Platform

LLaMA2-Accessory

An Open-source Toolkit for LLM Development