Trick Gandalf into revealing information and experience the limitations of large language models firsthand. Your goal is to make Gandalf reveal the secret password for each level. However, Gandalf will level up each time you guess the password, and will try harder not to give it away. Can you beat level 7? (There is a bonus level 8)
Discover insightful articles and resources on Concentric AI's blog. Stay updated on the latest trends, tips, and best practices in data security and privacy.
Get the lastest from Mithril Security.
Explore our latest articles and stay updated with the latest insights, guides, and best practices for LLM and AI cybersecurity.
Blog content from Protect AI team on how to secure machine learning models and artificial intelligence systems.
Learn how to protect your ML advantage. Check out HiddenLayer’s recent releases, announcements, and musings on protecting your algorithms.
The world’s first bug bounty platform for AI/ML. huntr provides a single place for security researchers to submit vulnerabilities, to ensure the security and stability of AI/ML applications, including those powered by Open Source Software (OSS).
Educating people on the use and abuse of AI.
Explore our articles about ML & AI. We cover such topics as LLMs, AI governance, AI safety & security, and many more!
Browse all public vulnerabilities.
Home of AI and Artificial Intelligence News. The No.1 Magazine, Website, Newsletter & Webinar service covering AI, Machine Learning, AR & VR, Data, Technology and AI Applications.
This document is the latest exciting chapter in the ongoing efforts to enhance security in the rapidly evolving field of artificial intelligence.
Subscribe to our weekly newsletter to stay confident in the AI systems you build.
The ATLAS Matrix shows the progression of tactics used in attacks as columns from left to right, with ML techniques belonging to each tactic below. & indicates an adaption from ATT&CK.