dreadnode / parleyLinks
Tree of Attacks (TAP) Jailbreaking Implementation
☆115Updated last year
Alternatives and similar repositories for parley
Users that are interested in parley are comparing it to the libraries listed below
Sorting:
- Data Scientists Go To Jupyter☆66Updated 6 months ago
- A YAML based format for describing tools to LLMs, like man pages but for robots!☆78Updated 4 months ago
- ☆53Updated this week
- source code for the offsecml framework☆41Updated last year
- A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)☆133Updated 8 months ago
- using ML models for red teaming☆44Updated 2 years ago
- An interactive CLI application for interacting with authenticated Jupyter instances.☆55Updated 4 months ago
- ☆66Updated last week
- A utility to inspect, validate, sign and verify machine learning model files.☆58Updated 7 months ago
- Code Repository for: AIRTBench: Measuring Autonomous AI Red Teaming Capabilities in Language Models☆77Updated this week
- ☆17Updated last year
- https://arxiv.org/abs/2412.02776☆62Updated 9 months ago
- Arxiv + Notion Sync☆20Updated 4 months ago
- Central repo for talks and presentations☆46Updated last year
- CLI and API server for https://github.com/dreadnode/robopages☆35Updated this week
- Example agents for the Dreadnode platform☆16Updated last month
- Experiments with Google Gemini's Vision capabilities for LLM driven/aided web navigation and desktop manipulation☆26Updated 7 months ago
- Stage 1: Sensitive Email/Chat Classification for Adversary Agent Emulation (espionage). This project is meant to extend Red Reaper v1 whi…☆42Updated last year
- MLOps Attack Toolkit☆27Updated 3 weeks ago
- Automated vulnerability discovery and annotation☆67Updated last year
- Payloads for Attacking Large Language Models☆99Updated 3 months ago
- General research for Dreadnode☆25Updated last year
- LLM Testing Findings Templates☆72Updated last year
- A Nemesis powered Retrieval-Augmented Generation (RAG) chatbot proof-of-concept.☆68Updated last month
- [IJCAI 2024] Imperio is an LLM-powered backdoor attack. It allows the adversary to issue language-guided instructions to control the vict…☆41Updated 6 months ago
- An experimental project exploring the use of Large Language Models (LLMs) to solve HackTheBox machines autonomously.☆61Updated last week
- Freyja is a Golang, Purple Team agent that compiles into Windows, Linux and macOS x64 executables.☆60Updated 10 months ago
- The Privacy Adversarial Framework (PAF) is a knowledge base of privacy-focused adversarial tactics and techniques. PAF is heavily inspire…☆58Updated 2 years ago
- Verizon Burp Extensions: AI Suite☆138Updated 4 months ago
- ☆33Updated 5 months ago