1 code implementation • 13 Nov 2019 • Rey Reza Wiyatno, Anqi Xu, Ousmane Dia, Archy de Berker
Recent research has found that many families of machine learning models are vulnerable to adversarial examples: inputs that are specifically designed to cause the target model to produce erroneous outputs.
no code implementations • 31 Jan 2019 • Laure Delisle, Alfredo Kalaitzis, Krzysztof Majewski, Archy de Berker, Milena Marin, Julien Cornebise
We report the first, to the best of our knowledge, hand-in-hand collaboration between human rights activists and machine learners, leveraging crowd-sourcing to study online abuse against women on Twitter.