Agent Security Hackathon: Expanding our Knowledge

What is Agent Security?

While much AI safety research focuses on large language models, the AI systems being deployed in the real world are far more complex. Enter the realm of Agents — sophisticated combinations of language models and programmed features that are reshaping our digital landscape.

During this hackathon, we'll put our research skills to the test by diving deep into the world of Agents:

• What are their unique safety properties?
• Under what conditions do they fail?
• How do they differ from raw language models?

Join us to uncover the unknowns of Agent security by signing up below!

The rapid advancement of AI technologies has brought about systems capable of increasingly autonomous operation. AI Agents, which integrate large language models with programmed functionalities, represent a significant step in this evolution. These Agents can make decisions, execute tasks, and interact with their environment in ways that surpass traditional AI systems.

This progression, while promising, introduces new challenges in ensuring the safety and security of AI systems. The complexity of AI Agents necessitates a reevaluation of existing safety frameworks and the development of novel approaches to security.

Submission

You will join in teams to submit a report and code repository of your research from this weekend with established researchers as judges looking through your project afterwards and providing reviews.