Analyzing Forward Robustness of Feedforward Deep Neural Networks with LeakyReLU Activation Function Through Symbolic Propagation

Giulio Masetti, Felicita Di Giandomenico. Analyzing Forward Robustness of Feedforward Deep Neural Networks with LeakyReLU Activation Function Through Symbolic Propagation. In Irena Koprinska, Michael Kamp, Annalisa Appice, Corrado Loglisci, Luiza Antonie, Albrecht Zimmermann, Riccardo Guidotti, Özlem Özgöbek, Rita P. Ribeiro, Ricard Gavaldà, João Gama 0001, Linara Adilova, Yamuna Krishnamurthy, Pedro M. Ferreira 0001, Donato Malerba, Ibéria Medeiros, Michelangelo Ceci, Giuseppe Manco 0001, Elio Masciari, Zbigniew W. Ras, Peter Christen, Eirini Ntoutsi, Erich Schubert, Arthur Zimek, Anna Monreale, Przemyslaw Biecek, Salvatore Rinzivillo, Benjamin Kille, Andreas Lommatzsch, Jon Atle Gulla, editors, ECML PKDD 2020 Workshops - Workshops of the European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2020): SoGood 2020, PDFL 2020, MLCS 2020, NFMCP 2020, DINA 2020, EDML 2020, XKDD 2020 and INRA 2020, Ghent, Belgium, September 14-18, 2020, Proceedings. Volume 1323 of Communications in Computer and Information Science, pages 460-474, Springer, 2020. [doi]