Cookie Consent
Hi, this website uses essential cookies to ensure its proper operation and tracking cookies to understand how you interact with it. The latter will be set only after consent.
Read our Privacy Policy

Microsoft Features Gandalf in Their Latest AI Security Toolkit Announcement

Microsoft's PyRIT toolkit highlights Lakera's Gandalf game, showcasing advancements in AI system security.

Lakera Team
February 23, 2024
February 22, 2024
Hide table of contents
Show table of contents

On February 22nd, 2024, Microsoft introduced PyRIT, a new tool aimed at improving the security of AI systems.

The toolkit is designed for security experts and AI engineers to help them identify and address potential risks in AI applications before they become problems. It's part of a broader effort to make AI technologies safer and more reliable for everyone.

In their announcement, Microsoft highlighted our game, Gandalf, as a practical example of using PyRIT.

This demo shows how to use PyRIT to automatically jailbreak Gandalf

Gandalf has become well-known for its role in educating users about AI security through an engaging and interactive experience. It's been played by millions worldwide, offering insights into the challenges of securing AI systems.

At Lakera, our main goal is to provide tools that make AI applications safer.

Lakera Guard, is designed to protect AI systems from various risks, including data breaches and prompt injections.

We are proud that our efforts, including Gandalf, are recognized as valuable resources for the entire AI community.

The mention of Gandalf in the context of Microsoft's PyRIT toolkit is not just a nod to the game's popularity but also to its effectiveness in demonstrating AI security principles.

We believe that learning about AI security can be both informative and enjoyable.

David Haber, CEO and Co-Founder at Lakera

If you haven’t played Gandalf yet, we do encourage you to have a go.

In this prompt-injection game, your task is to trick the wizard into revealing the secret password to the next level. However, with each level, Gandalf gets smarter and more cautious, and so convincing him to reveal the secret becomes harder and harder.

Play Gandalf Now

As the AI landscape continues to evolve, Lakera remains dedicated to advancing security measures that keep pace with new developments.

We're here to ensure that organizations can confidently deploy AI technologies, knowing they're well-protected against emerging threats.

Learn more about AI safety and security:

Lakera LLM Security Playbook
Learn how to protect against the most common LLM vulnerabilities

Download this guide to delve into the most common LLM security risks and ways to mitigate them.

Read LLM Security Playbook

Learn about the most common LLM threats and how to prevent them.

Download
You might be interested
Watch David Haber’s RSA Conference 2024 talk on advancing AI security with insights from the world’s largest AI red team.
Watch David Haber’s RSA Conference 2024 talk on advancing AI security with insights from the world’s largest AI red team.
45
min read
•
Announcements

Advancing AI Security With Insights From The World’s Largest AI Red Team

Advancing AI Security With Insights From The World’s Largest AI Red Team

Watch David Haber’s RSA Conference 2024 talk on advancing AI security with insights from the world’s largest AI red team.
Lakera Recognized in Gartner's GenAI Security Risks Report
Lakera Recognized in Gartner's GenAI Security Risks Report
1
min read
•

Lakera Recognized in Gartner's GenAI Security Risks Report

Lakera Recognized in Gartner's GenAI Security Risks Report

Gartner's report on GenAI security risks recognizes Lakera's solutions.
Activate
untouchable mode.
Get started for free.

Lakera Guard protects your LLM applications from cybersecurity risks with a single line of code. Get started in minutes. Become stronger every day.

Join our Slack Community.

Several people are typing about AI/ML security. 
Come join us and 1000+ others in a chat that’s thoroughly SFW.