davidwillisowen / IPIMLinks
Indirect Prompt Injection Methodology (IPIM) - A structured process which security professionals can use to find Indirect Prompt Injection vulnerabilities in LLMs and produce POCs.
☆13Updated 3 months ago
Alternatives and similar repositories for IPIM
Users that are interested in IPIM are comparing it to the libraries listed below
Sorting:
- All things specific to LLM Red Teaming Generative AI☆29Updated last year
- A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)☆145Updated 11 months ago
- ☆63Updated last week
- Tree of Attacks (TAP) Jailbreaking Implementation☆115Updated last year
- ☆107Updated last week
- source code for the offsecml framework☆43Updated last year
- Reference notes for Attacking and Defending Generative AI presentation☆67Updated last year
- ☆21Updated 11 months ago
- ☆43Updated 11 months ago
- ☆17Updated last year
- Code Repository for: AIRTBench: Measuring Autonomous AI Red Teaming Capabilities in Language Models☆90Updated this week
- Stage 1: Sensitive Email/Chat Classification for Adversary Agent Emulation (espionage). This project is meant to extend Red Reaper v1 whi…☆42Updated last year
- using ML models for red teaming☆44Updated 2 years ago
- AI-Powered, Local Pythonic Coding Agent 🐞💻☆24Updated 8 months ago
- ☆18Updated 7 months ago
- Arxiv + Notion Sync☆20Updated 6 months ago
- [IJCAI 2024] Imperio is an LLM-powered backdoor attack. It allows the adversary to issue language-guided instructions to control the vict…☆43Updated 9 months ago
- Example agents for the Dreadnode platform☆19Updated this week
- LLM | Security | Operations in one github repo with good links and pictures.☆66Updated 10 months ago
- A YAML based format for describing tools to LLMs, like man pages but for robots!☆79Updated 6 months ago
- A curated list of awesome AI Red Teaming resources and tools.☆27Updated 2 years ago
- Manual Prompt Injection / Red Teaming Tool☆48Updated last year
- CALDERA plugin for adversary emulation of AI-enabled systems☆103Updated 2 years ago
- Autonomous Assumed Breach Penetration-Testing Active Directory Networks☆29Updated 3 weeks ago
- TTPMapper is an AI-driven threat intelligence parser that converts unstructured reports whether from web URLs or PDF files into structure…☆46Updated 5 months ago
- ☆81Updated this week
- [EMNLP 2024] Holistic Automated Red Teaming for Large Language Models through Top-Down Test Case Generation and Multi-turn Interaction☆17Updated last year
- Data Scientists Go To Jupyter☆67Updated 8 months ago
- A structured red-team prompt for generating ethical hacking tools using AI - designed for use in labs, CTFs, and authorized security asse…☆23Updated 4 months ago
- The notebook for my talk - ChatGPT: Your Red Teaming Ally☆50Updated 2 years ago