no code implementations • 28 Sep 2022 • Jože M. Rožanec, Dimitrios Papamartzivanos, Entso Veliou, Theodora Anastasiou, Jelle Keizer, Blaž Fortuna, Dunja Mladenić
We propose using a two-layered deployment of machine learning models to prevent adversarial attacks.
no code implementations • 12 Sep 2022 • Jože M. Rožanec, Luka Bizjak, Elena Trajkova, Patrik Zajec, Jelle Keizer, Blaž Fortuna, Dunja Mladenić
Our results show that the explored active learning settings can reduce the data labeling effort by between three and four percent without detriment to the overall quality goals, considering a threshold of p=0. 95.