- Inicio
- RESULTADOS DE INVESTIGACIÓN
- Listar RESULTADOS DE INVESTIGACIÓN por autor
Listar RESULTADOS DE INVESTIGACIÓN por autor "Nakamura, Kazuaki"
Mostrando ítems 1-1 de 1
-
Social IoT Approach to Cyber Defense of a Deep-Learning-Based Recognition System in front of Media Clones Generated by Model Inversion Attack
Khosravy, Mahdi; Nakamura, Kazuaki; Nitta, Naoko; Dey, Nilanjan; González-Crespo, Rubén; Herrera-Viedma, Enrique; Babaguchi, Noboru (IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2023)Model inversion attack (MIA) is a cyber threat with an increasing alert even for deep-learning-based recognition systems (DLRSs). By targeting a DLRS under a scenario of attacker access to the model structure and parameters, ...