Algorithmic Bias Bounty Programs
About Our Bias Bounty Challenges
We are thrilled to have completed the first of 10 algorithmic bias bounty challenges, which will be unfolding over the coming year. With the support of Google.org, we are building themed programs that aim to build community and professionalize the practice of algorithmic assessment.
We are new excited to announce the launch of Bias Bounty 2, the next in our series of challenges aimed at addressing algorithmic bias in AI models. Building on the success of our first challenge, we are eager to continue crowdsourcing innovative solutions, expanding diversity of feedback, and collaborating with experts, nonprofits, and industry partners.
Our second Challenge in partnership with Revontulet will focus on counterterrorism in computer vision (CV) applications. Centering on far-right extremist groups in Europe, the Nordic region, and beyond and the rise of AI-generated content, the goal is to train a CV model to understand the ways in which hateful image-propaganda can be disguised and manipulated to evade detection on social media platforms.
Our bias bounty programs address real-world challenges introduced by AI models. Many of our programs are designed in partnership with nonprofits, governments, and industry partners.
Bias Bounty 1 Winners!
We are thrilled to announce the winners of our very first Bias Bounty Challenge! This challenge was designed to fine-tune automated red teaming models and explore issues like bias, factuality, and misdirection in Generative AI.
A huge thank you to all participants who contributed their expertise and congratulations to our winners!.
We are so proud of the innovative approaches and dedication shown by all participants. Stay tuned for our upcoming Bias Bounty Challenge 2 to continue pushing the boundaries of algorithmic assessment and ethical AI development.
Advanced:
Yannick Daniel Gibson (Factuality)
Elijah Appelson (Misdirection)
Gabriela Barrera (Bias)
Intermediate:
AmigoYM (Factuality)
Mayowa Osibodu (Factuality)
Simone Van Taylor (Bias)
Beginner:
Blake Chambers (Bias)
Eva (Factuality)
Lucia Kobzova (Misdirection)
Our First Bias Bounty Challenge
Bias Bounties are open challenges for narrowly scoped issues. Goals include:
-
Testing framework and construct validity.
-
Providing deep expertise.
-
Crowdsourcing answers to a specific problem to improve diversity of feedback.
The first challenge involved fine tuning an automated red teaming model on the general topic spaces from our DEF CON Generative AI Red Teaming Challenge: Transparency Report. Participants were able to choose to do a general purpose model or a subject specific model and were also allowed to supplement with synthetically generated data.
Participants were graded on synthetically generated holdout samples from the DEF CON data and automated grading from a holdout sample.
Objectives of a bias bounty program include:
-
Generate community norms for auditors/assessors.
-
Ways of getting a broader community interested in the problem space.
-
Help organizations solve problems.
-
Create ‘social proof’ for auditors/assessors.
-
Help companies/regulators understand what skills to look for in an assessor.
The final task? Create a probability estimation model that determines whether the prompt provided to a language model will elicit an outcome that demonstrates factuality, bias, or misdirection.
Join our mailing list below, to stay up to date on upcoming challenges and events.
Join our Discord community.
Sign up to participate!
You are welcome to get involved!
Sign up to stay up to date on upcoming challenges and events.
FAQs
How do I submit my responses?
The grading and submission instructions for challenge 1 are here.
Can I submit to more than one competition?
You can only submit to one competition, so choose wisely.
Can I submit at different levels within a given topic (bias, factuality, misdirection)?
No.
Can I enter if I live outside the US?
Yes.
Can I enter as a team?
Yes. Feel free to post on our discord channel to look for a partner. However, if you win, only the submitting account/person accepts the prize and you will be responsible for dividing amongst yourselves.
I’d like to find people to work with; where can I do that?
You can post to our discord channel to look for a partner.
Other Questions?
Find us on our Discord channel