M. Christakis

activity

20172024

most citedRAID: Randomized Adversarial-Input Detection for Neural Networks

13 citations · 42 across the 13 of their papers we have counts for

collaborators

Showing 2022Show all

1 paper · 1 filter

cs.LG2022

Specifying and Testing $k$ -Safety Properties for Machine-Learning Models

Maria Christakis, Hasan Ferit Eniser, Jörg Hoffmann +2

Machine-learning models are becoming increasingly prevalent in our lives, for instance assisting in image-classification or decision-making tasks. Consequently, the reliability of…

Specifying and Testing k-Safety Properties for Machine-Learning Models

Specifying and Testing $k$ -Safety Properties for Machine-Learning Models