BishopFox / BrokenHillLinks
A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)
☆113Updated 5 months ago
Alternatives and similar repositories for BrokenHill
Users that are interested in BrokenHill are comparing it to the libraries listed below
Sorting:
- Integrate PyRIT in existing tools☆25Updated 3 months ago
- ☆43Updated last week
- Tree of Attacks (TAP) Jailbreaking Implementation☆109Updated last year
- source code for the offsecml framework☆40Updated 11 months ago
- Verizon Burp Extensions: AI Suite☆130Updated last month
- ☆14Updated 5 months ago
- An interactive CLI application for interacting with authenticated Jupyter instances.☆53Updated 3 weeks ago
- A YAML based format for describing tools to LLMs, like man pages but for robots!☆71Updated last month
- Project Mantis: Hacking Back the AI-Hacker; Prompt Injection as a Defense Against LLM-driven Cyberattacks☆67Updated last week
- A LLM explicitly designed for getting hacked☆149Updated last year
- Curated list of Open Source project focused on LLM security☆43Updated 6 months ago
- NOVA: The Prompt Pattern Matching☆111Updated last month
- A research project to add some brrrrrr to Burp☆169Updated 3 months ago
- Payloads for Attacking Large Language Models☆89Updated 10 months ago
- A knowledge source about TTPs used to target GenAI-based systems, copilots and agents☆38Updated 3 months ago
- A collection of prompt injection mitigation techniques.☆22Updated last year
- Delving into the Realm of LLM Security: An Exploration of Offensive and Defensive Tools, Unveiling Their Present Capabilities.☆162Updated last year
- Awesome products for securing AI systems includes open source and commercial options and an infographic licensed CC-BY-SA-4.0.☆63Updated 11 months ago
- A Caldera plugin for the emulation of complete, realistic cyberattack chains.☆53Updated 2 months ago
- Reference notes for Attacking and Defending Generative AI presentation☆61Updated 10 months ago
- Stage 1: Sensitive Email/Chat Classification for Adversary Agent Emulation (espionage). This project is meant to extend Red Reaper v1 whi…☆41Updated 9 months ago
- AIGoat: A deliberately Vulnerable AI Infrastructure. Learn AI security through solving our challenges.☆235Updated last month
- The Arcanum Prompt Injection Taxonomy☆94Updated 2 weeks ago
- Automated vulnerability discovery and annotation☆67Updated 10 months ago
- using ML models for red teaming☆43Updated last year
- [IJCAI 2024] Imperio is an LLM-powered backdoor attack. It allows the adversary to issue language-guided instructions to control the vict…☆41Updated 3 months ago
- ☆40Updated 5 months ago
- LLM Testing Findings Templates☆72Updated last year
- A very simple open source implementation of Google's Project Naptime☆150Updated 2 months ago
- Data Scientists Go To Jupyter☆64Updated 3 months ago