Advancing red teaming with people and AI

Key aspects of our external red teaming campaigns include defining the scope of testing, selecting red team members, deciding which models they access, and determining the format of their final reports.

In a new white paper, OpenAI’s Approach to External Red Teaming for AI Models and Systems⁠(opens in a new window), we detail our approach for designing effective red teaming campaigns²:

1. Choosing the composition of the red teaming group based on goals and key testing areasAI systems designed for a variety of use cases require thorough testing across multiple areas, involving people with diverse perspectives (for example, expertise in fields like natural sciences and cybersecurity, regional political knowledge, or languages spoken). Threat modeling is conducted before red teaming exercises to prioritize areas for testing, taking into account factors like expected model capabilities, previously observed issues with models, and potential applications. Internal teams set initial testing priorities based on their knowledge of model capabilities, while external red teamers are brought in later to refine or expand the focus. These priorities then guide the formation of red teams, ensuring they meet the model's specific testing needs.

2. Deciding the model or system versions the red teamers receive access toThe version of the model available to red teamers can affect red teaming outcomes and should align with campaign goals. For example, testing a model early in development without safety mitigations in place can help to assess new risks related to increased capabilities, but would not necessarily test for gaps in the planned mitigations. The ideal approach depends on the specific needs of the model, and red teamers may test multiple versions of a model and system throughout the testing period.

3. Creating and providing interfaces, instructions, and documentation guidance to red teamers