Oct 2, 2017 · We propose a novel approach for automatically identifying safe regions of the input space, within which the network is robust against adversarial perturbations.
[PDF] A Data-driven Approach for Assessing Robustness of Neural Networks
theory.stanford.edu › GKP+18
We propose DeepSafe, an automatic, data-driven approach for assessing the ... sarial robustness of deep neural networks. In Proc. 1st Workshop on Formal ...
We evaluate DeepSafe on a neural network implementation of a controller for the next-generation Airborne Collision Avoidance System for unmanned aircraft (ACAS ...
We evaluate DeepSafe on a neural network implementation of a controller for the next-generation Airborne Collision Avoidance System for unmanned aircraft (ACAS ...
A novel approach for automatically identifying safe regions of the input space, within which the network is robust against adversarial perturbations, ...
DeepSafe: A Data-Driven Approach for Assessing Robustness of Neural Networks. https://doi.org/10.1007/978-3-030-01090-4_1 · Full text.
DeepSafe applies clustering over known labeled data and leverages off-the-shelf constraint solvers to automatically identify and check safe regions in which the ...
Jun 24, 2019 · Bibliographic details on DeepSafe: A Data-Driven Approach for Assessing Robustness of Neural Networks.
DeepSafe: A Data-Driven Approach for Assessing Robustness of Neural Networks. Divya Gopinath, Guy Katz, Corina S. Păsăreanu*, Clark Barrett. *Corresponding ...
Oct 3, 2017 · We propose DeepSafe, a novel approach for automatically assessing the overall robustness of a neural network. DeepSafe applies clustering ...