-
Python library for direct and indirect discrimination prevention in data mining
This python library implements the discrimination discovery and prevention method proposed in the paper: “A methodology for direct and indirect discrimination prevention in...-
GitHub
The resource: 'Link to library' is not accessible as guest user. You must login to access it!
-
GitHub
-
Label flipping attacks in Federated Learning
The following experiments showcase Federated Learning using Scikit-learn.-
ipynb
The resource: 'FederatedLearning-sklearn' is not accessible as guest user. You must login to access it!
-
ipynb
-
Private Deliverable D2.3 Report on WP2 activities
-
An ethico-legal framework for social data science
This paper presents a framework for research infrastructures enabling ethically sensitive and legally compliant data science in Europe. Our goal is to describe how to design... -
Algorithmic decision making and the cost of fairness
Algorithms are now regularly used to decide whether defendants awaiting trial are too dangerous to be released back into the community. In some cases, black defendants are... -
Bias in algorithmic filtering and personalization
Online information intermediaries such as Facebook and Google are slowly replacing traditional media channels thereby partly becoming the gatekeepers of our society. To deal... -
Accountability for the Use of Algorithms in a Big Data Environment
Accountability is the ability to provide good reasons in order to explain and to justify actions, decisions, and policies for a (hypothetical) forum of persons or... -
Algorithmic Accountability and Public Reason
The ever-increasing application of algorithms to decision-making in a range of social contexts has prompted demands for algorithmic accountability. Accountable decision-makers... -
A Survey of Methods for Explaining Black Box Models
In recent years, many accurate decision support systems have been constructed as black boxes, that is as systems that hide their internal logic to the user. This lack of... -
A qualitative exploration of perceptions of algorithmic fairness
Algorithmic systems increasingly shape information people are exposed to as well as influence decisions about employment, finances, and other opportunities. In some cases,... -
AI and Big Data A blueprint for a human rights and social and ethical impact ...
Building on studies of the collective dimension of data protection, this article sets out to embed this new perspective in an assessment model centred on human rights (Human...
