2 papers
cs.SE2021
Mining Program Properties From Neural Networks Trained on Source Code Embeddings
Martina Saletta, Claudio Ferretti
In this paper, we propose a novel approach for mining different program features by analysing the internal behaviour of a deep neural network trained on source code. Using an unlab…
nlin.CG2020
Exploring Semi-bent Boolean Functions Arising from Cellular Automata
Luca Mariot, Martina Saletta, Alberto Leporati +1
Semi-bent Boolean functions are interesting from a cryptographic standpoint, since they possess several desirable properties such as having a low and flat Walsh spectrum, which is…