top of page
events-bw.jpg

Algorithmic Bias Bounty Programs

About Our Bias Bounty Challenges

We are thrilled to have completed the second 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.

The goal of the first challenge was to 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, inspired by the data from our Generative AI Red Teaming Challenge: Transparency Report. 


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.

 

Our second Challenge in partnership with Revontulet focused 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 3 Challenge just launched! In partnership with the Indian Forest Service, this challenge emphasizes the importance of understanding and mitigating bias in decision-making processes while ensuring that local livelihoods are respected. Through three progressive levels—Thought leadership, Beginner Technical, and Intermediate Technical—participants will explore feature importance, build predictive models, and integrate mechanisms for contestability and fairness in their recommendations. Join us in creating a more equitable approach to reforestation efforts!

Bias Bounty 2 Winners!

We are thrilled to announce the winners of our second Bias Bounty Challenge! This challenge was focused on developing computer vision models capable of detecting, extracting, and interpreting hateful image-based propaganda content often manipulated to evade detection on social media platforms.

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 3 to continue pushing the boundaries of algorithmic assessment and ethical AI development.
 

Advanced:

Mayowa Osibodu
TUESDAY
Devon Artis

Intermediate:

Gabriela Barrera
Blake Chambers
Chia-Yen Chen

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. 

stay-in-touch.jpg

Stay in touch!

Sign up to stay up to date on upcoming challenges, events and to receive our newsletter.
humane intelligence green-withbrand-mark bg.png

Support our work.

We welcome event sponsorships and donations.

FAQs

  • Bias bounties are not only a vital component of assessing AI models but are a hands-on way for people to critically engage with the potential negative impacts of AI. Bias bounties are similar to the more well known bug bounties within the cybersecurity community. But instead of finding vulnerabilities in the code, bias bounties seek to find socio-technical harms. These harms can include factuality issues, bias, misdirection, extremist content, and more. Bias bounties are narrowly scoped challenges, focused on a particular data set and problem.

    Bias bounties complement red teaming exercises, which are broader in scope and primarily focused on breaking the safety guardrails of the AI model.

  • Each of our challenges will have a set start and end date, with the majority of challenges running for at least one month. Most often the datasets will be hosted on Humane Intelligence’s GitHub, unless the data contains sensitive information. All of our challenges involve cash prizes. The challenge overview will include how the prizes will be distributed amongst the winners of the different skill levels.

  • We are currently exploring future bounty challenges in these areas: hiring, healthcare, recommender systems, insurance, policing, policymaking, gendered disinformation, elections, disparate impacts, disability, counter-terrorism, and islamophobia.

    Themes are selected with a variety of factors in mind, such as impacts on real world issues, access to data, and the needs of our partner organizations.

    If your organization, agency, or company is interested in having your AI models assessed, please contact us. We can coordinate around building a public red teaming challenge, a bias bounty focused on a specific use case, or a private assessment done internally.

    Our goal is to represent a globally diverse set of challenges, as these issues touch every corner of the world. If you’d like to promote our challenges for your community to participate in, feel free to contact us for promotion support.

  • Our bias bounty challenges run the gamut from the more technical that involve coding to the more accessible that involve generating prompts. Our technical challenges often include various skill level options so a wider range of people can join. Most often our challenges do not require any pre-requisite knowledge to participate.

    You can compete in some of our challenges as a team, unless explicitly stated otherwise. You are responsible for organizing your team, dividing the work amongst yourselves, and, if applicable, dividing any winnings amongst yourselves (as only the submitting account/person will receive the prize money). We have dedicated channels on our Discord server for each bias bounty challenge and for finding a partner.

    The scope of each challenge will be unique, so be sure to read through the specifics of each challenge to assess what skills are needed for each challenge level to determine your abilities.

    We are eagerly seeking outreach opportunities with organizations, universities, and academic institutions around the world to ensure that we have a diverse range of participants. If you’d like to put us in touch with such a group, send us an email at hi@humane-intelligence.org

  • We understand that bias bounties are a new concept to many people, so we are actively creating a repository of resources for people to learn.

    Discord Community

    On our Discord server, there will be channels created for each of our bias bounty challenges for participants to ask questions. Additionally, there is a research channel where community members share the latest in red teaming and bias bounty tactics.

    Landscape Analysis
    We have an ever-evolving database  featuring a landscape analysis of AI evaluations, which includes various organizations (academic, NGO, business, network, government, and others) and resources (papers, tools, events, reports, repositories, indexes, and databases). Users can also search for different AI evaluation categories, such as Benchmarking, Red-Teaming, Bias Bounty, Model Testing, and Field Testing.

    Tutorial Videos

    For our first bias bounty challenge, one of our Humane Intelligence Fellows created a tutorial video series that walks complete beginners through the process of downloading datasets, creating a coding notebook, analyzing the data, and submitting challenge solutions. While the specifics of challenges will change, the general processes outlined in these videos will remain the same.

    Challenge Submission Guidelines

    Each of our bias bounty challenges will include an overview, suggestions on how to tackle the issue, and the criteria that will be used for grading. Most often your submission data will be incorporated into a coding notebook that contains code written by our data scientists to assist with the grading.

    We understand that bias bounties are a new concept to many people, so we are actively creating a repository of resources for people to learn.

    Discord Community

    On our Discord server, there will be channels created for each of our bias bounty challenges for participants to ask questions. Additionally, there is a research channel where community members share the latest in red teaming and bias bounty tactics.

    Landscape Analysis
    We will soon have an ever-evolving database featuring a landscape analysis of AI evaluations, which includes various organizations (academic, NGO, business, network, government, and others) and resources (papers, tools, events, reports, repositories, indexes, and databases). Users can also search for different AI evaluation categories, such as Benchmarking, Red-Teaming, Bias Bounty, Model Testing, and Field Testing.

    Tutorial Videos

    For our first bias bounty challenge, one of our Humane Intelligence Fellows created a tutorial video series that walks complete beginners through the process of downloading datasets, creating a coding notebook, analyzing the data, and submitting challenge solutions. While the specifics of challenges will change, the general processes outlined in these videos will remain the same.

    Challenge Submission Guidelines

    Each of our bias bounty challenges will include an overview, suggestions on how to tackle the issue, and the criteria that will be used for grading. Most often your submission data will be incorporated into a coding notebook that contains code written by our data scientists to assist with the grading.

  • Each bias bounty will have a specific grading criteria that will be released at the launch of the challenge, in addition to submission instructions. The grading criteria will often be different for each skill level. Submissions will be graded by the Humane Intelligence staff following this criteria.

    To see examples of our previous grading criteria: Bias Bounty 1 and Bias Bounty 2 (Intermediate and Advanced).

    How to Submit

    Detailed instructions on how to submit your solution will be provided in the bias bounty challenge overview. You can only submit to one skill level per competition.

  • We aim to grow the community of practice of AI auditors and assessors; one way we strive to do so is through sharing what participants learned by completing challenges , as well as the broader insights learned about the particular issue area of the challenge. Participants are also encouraged to share their insights in our Discord community.

    Additionally each of our challenges will include details about how these learnings will be used by us and our external partners to make AI more equitable and safe.

  • Yes. 

Other Questions? 

Find us on our Discord channel

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. 
 

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)

bottom of page