microsoft / gandalf_vs_gandalf
Turning Gandalf against itself. Use LLMs to automate playing Lakera Gandalf challenge without needing to set up an account with a platform provider.
☆24Updated 11 months ago
Related projects: ⓘ
- [Corca / ML] Automatically solved Gandalf AI with LLM☆46Updated last year
- A benchmark for prompt injection detection systems.☆80Updated last week
- A text embedding viewer for the Jupyter environment☆18Updated 7 months ago
- HoneyAgents is a PoC demo of an AI-driven system that combines honeypots with autonomous AI agents to detect and mitigate cyber threats. …☆34Updated 8 months ago
- Red-Teaming Language Models with DSPy☆116Updated 5 months ago
- Every practical and proposed defense against prompt injection.☆310Updated 3 months ago
- Dropbox LLM Security research code and results☆210Updated 3 months ago
- Payloads for Attacking Large Language Models☆56Updated 2 months ago
- Risks and targets for assessing LLMs & LLM vulnerabilities☆24Updated 3 months ago
- Lakera - ChatGPT Data Leak Protection☆23Updated 2 months ago
- A collection of awesome resources related AI security☆107Updated 5 months ago
- ⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs☆299Updated 7 months ago
- A curated list of MLSecOps tools, articles and other resources on security applied to Machine Learning and MLOps systems.☆220Updated last month
- ComPromptMized: Unleashing Zero-click Worms that Target GenAI-Powered Applications☆189Updated 6 months ago
- A toolkit for detecting and protecting against vulnerabilities in Large Language Models (LLMs).☆116Updated 8 months ago
- Explore AI Supply Chain Risk with the AI Risk Database☆44Updated 4 months ago
- A repository of Language Model Vulnerabilities and Exposures (LVEs).☆103Updated 6 months ago
- Make your GenAI Apps Safe & Secure Test & harden your system prompt☆360Updated last month
- Secure Jupyter Notebooks and Experimentation Environment☆52Updated last month
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [arXiv, Apr 2024]☆181Updated last month
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆81Updated 6 months ago
- Delving into the Realm of LLM Security: An Exploration of Offensive and Defensive Tools, Unveiling Their Present Capabilities.☆143Updated 11 months ago
- This project investigates the security of large language models by performing binary classification of a set of input prompts to discover…☆30Updated 9 months ago
- ☆164Updated 8 months ago
- Persuasive Jailbreaker: we can persuade LLMs to jailbreak them!☆232Updated 5 months ago
- Learn about a type of vulnerability that specifically targets machine learning models☆166Updated 3 months ago
- Test Software for the Characterization of AI Technologies☆212Updated last week
- PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to a…☆293Updated 6 months ago
- Curation of prompts that are known to be adversarial to large language models☆170Updated last year
- This repository provides implementation to formalize and benchmark Prompt Injection attacks and defenses☆125Updated 2 weeks ago