4 papers
Robust Federated Learning via Byzantine Filtering over Encrypted Updates
Adda Akram Bendoukha, Aymen Boudguiga, Nesrine Kaaniche +3
Federated Learning (FL) aims to train a collaborative model while preserving data privacy. However, the distributed nature of this approach still raises privacy and security issues…
Measuring the Hidden Cost of Data Valuation through Collective Disclosure
Patrick Mesana, Gilles Caporossi, Sebastien Gambs
Data valuation methods assign marginal utility to each data point that has contributed to the training of a machine learning model. If used directly as a payout mechanism, this cre…
On the Usage of Gaussian Process for Efficient Data Valuation
Clément Bénesse, Patrick Mesana, Athénaïs Gautier +1
In machine learning, knowing the impact of a given datum on model training is a fundamental task referred to as Data Valuation. Building on previous works from the literature, we h…
AI-Powered Cow Detection in Complex Farm Environments
Voncarlos M. Araújo, Ines Rili, Thomas Gisiger +4
Animal welfare has become a critical issue in contemporary society, emphasizing our ethical responsibilities toward animals, particularly within livestock farming. The advent of Ar…