Fairness Score and process standardization: framework for fairness certification in artificial intelligence systems
Avinash Agarwal,Harshna Agarwal,Nihaarika Agarwal +2 more
TL;DR: In this paper , the authors proposed a novel Fairness Score to measure the fairness of a data-driven AI system and a Standard Operating Procedure (SOP) for issuing Fairness Certification for such systems.
read more
Abstract: Decisions made by various Artificial Intelligence (AI) systems greatly influence our day-to-day lives. With the increasing use of AI systems, it becomes crucial to know that they are fair, identify the underlying biases in their decision-making, and create a standardized framework to ascertain their fairness. In this paper, we propose a novel Fairness Score to measure the fairness of a data-driven AI system and a Standard Operating Procedure (SOP) for issuing Fairness Certification for such systems. Fairness Score and audit process standardization will ensure quality, reduce ambiguity, enable comparison and improve the trustworthiness of the AI systems. It will also provide a framework to operationalise the concept of fairness and facilitate the commercial deployment of such systems. Furthermore, a Fairness Certificate issued by a designated third-party auditing agency following the standardized process would boost the conviction of the organizations in the AI systems that they intend to deploy. The Bias Index proposed in this paper also reveals comparative bias amongst the various protected attributes within the dataset. To substantiate the proposed framework, we iteratively train a model on biased and unbiased data using multiple datasets and check that the Fairness Score and the proposed process correctly identify the biases and judge the fairness.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
La nueva realidad de la educación ante los avances de la inteligencia artificial generativa
Francisco José García Peñalvo,Faraón Llorens-Largo,Javier Vidal +2 more
TL;DR: Las tecnologías generativas de IA en educación tienen un alto potencial, pero también presentan desafíos. Las herramientas como ChatGPT mejoran rápidamente, pero no tienen capacidad de razonamiento ni comprensión, y se basan en lenguajes de modelo de gran tamaño con una base probabilística.
71
A seven-layer model with checklists for standardising fairness assessment throughout the AI lifecycle
Avinash Agarwal,Harshna Agarwal +1 more
TL;DR: In this paper , the authors proposed a comprehensive approach in the form of a novel seven-layer model, inspired by the Open System Interconnection (OSI) model, to standardise AI fairness handling.
11
Certification of machine learning applications in the context of trustworthy AI with reference to the standardisation of AI systems
Martin L Levene,Jeffrey M. Wooldridge +1 more
- 17 Apr 2023
TL;DR: This study reviews the role of standards and certification in trustworthy AI, emphasizing the importance of uncertainty quantification and third-party certification in enhancing transparency and trust in AI systems, particularly in the UK's national quality infrastructure.
4
A step toward building a unified framework for managing AI bias
Saadia Afzal Rana,Zati Hakim Azizul,Ali Afzal Awan +2 more
TL;DR: This article thoroughly evaluates existing knowledge to enhance fairness management, which will serve as a foundation for creating a unified framework to address any bias and its subsequent mitigation method throughout the AI development pipeline.
4
The Influence of Gender and Skin Colour on the Watchlist Imbalance Effect in Facial Identification Scenarios
TL;DR: This study investigates the watchlist imbalance effect in facial identification, finding that skin colour significantly impacts performance, with dark skin tones experiencing disadvantageous bias, while gender also plays a role in the differential performance of AI algorithms.
3
References
Dissecting racial bias in an algorithm used to manage the health of populations
TL;DR: It is suggested that the choice of convenient, seemingly effective proxies for ground truth can be an important source of algorithmic bias in many contexts.
•Proceedings Article
Equality of opportunity in supervised learning
Moritz Hardt,Eric Price,Nathan Srebro +2 more
- 05 Dec 2016
TL;DR: This work proposes a criterion for discrimination against a specified sensitive attribute in supervised learning, where the goal is to predict some target based on available features and shows how to optimally adjust any learned predictor so as to remove discrimination according to this definition.
Fairness through awareness
Cynthia Dwork,Moritz Hardt,Toniann Pitassi,Omer Reingold,Richard S. Zemel +4 more
- 08 Jan 2012
TL;DR: A framework for fair classification comprising a (hypothetical) task-specific metric for determining the degree to which individuals are similar with respect to the classification task at hand and an algorithm for maximizing utility subject to the fairness constraint, that similar individuals are treated similarly is presented.
Big Data's Disparate Impact
Solon Barocas,Andrew D. Selbst +1 more
TL;DR: In the absence of a demonstrable intent to discriminate, the best doctrinal hope for data mining's victims would seem to lie in disparate impact doctrine as discussed by the authors, which holds that a practice can be justified as a business necessity when its outcomes are predictive of future employment outcomes, and data mining is specifically designed to find such statistical correlations.
2.8K
•Posted Content
Fairness Through Awareness
TL;DR: In this article, the authors proposed a framework for fair classification comprising a task-specific metric for determining the degree to which individuals are similar with respect to the classification task at hand, and an algorithm for maximizing utility subject to the fairness constraint that similar individuals are treated similarly.
2.8K