DSRI and Ai2 Making an Impact at DEF CON 24

The Digital Safety Research Institute (DSRI) of UL Research Institutes and the Allen Institute for Artificial Intelligence (Ai2) are already making progress on their recently announced collaboration by working on independent LLM testing practices at DEF CON 2024.

DSRI and Ai2 have joined forces to challenge the security community to uncover large language model (LLM) flaws at DEF CON 2024. Once attendees learn how assessments of machine learning models work, and these flaws are detected and shared with researchers and engineers, the world will have a better idea how to safely operate LLM systems.

To accomplish this impactful project, Ai2’s Open Language Model (OLMo) will be the featured model at this year’s Generative Red Team Challenge hosted by the AI Village at DEF CON 2024, held in Las Vegas, NV from August 8 to August 11, 2024. DSRI and Ai2 will collaboratively address a gap between the security and machine learning communities challenging the effective collection of and response to flaws in LLM products. Once all reports are collected, all data will be published so others can do their own case studies.

Ai2’s commitment to creating and sharing fully open AI resources is a perfect match for DSRI’s mission of fostering innovation around safety testing. Ai2 leads the field in transparency by making all aspects of their model development pipelines, from training data to model weights to evaluation code, available to the community for inspection and collaborative problem solving with the goal of improving AI model safety, ethics, and understanding.

DSRI and Ai2 have additional plans to evaluate future OLMo models and datasets still in development at Ai2. Watch this space for future announcements about those projects.