2 papers
cs.LG2024
A New Dataset and Methodology for Malicious URL Classification
Ilan Schvartzman, Roei Sarussi, Maor Ashkenazi +3
Malicious URL (Uniform Resource Locator) classification is a pivotal aspect of Cybersecurity, offering defense against web-based threats. Despite deep learning's promise in this ar…
cs.LG2021
Towards Understanding Learning in Neural Networks with Linear Teachers
Roei Sarussi, Alon Brutzkus, Amir Globerson
Can a neural network minimizing cross-entropy learn linearly separable data? Despite progress in the theory of deep learning, this question remains unsolved. Here we prove that SGD…