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.
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.
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:
