Synchronization for neural networks over event-triggered multi-channel: Relay channels under cyber-attacks

Abstract

This work addresses synchronization for master–slave neural networks (MSNNs) with remote transmission. To reduce the communication frequency, an event-triggered strategy combined with a dynamically adjusted threshold is employed. For the sake of enhancing the information transmission quality, a relay channels protocol that considers cyber-attacks is established, acknowledging that occurrence rates of cyber-attacks may vary across different channels. Furthermore, regarding the limited capacity of channels, the current research considers a multi-channel transmission mechanism, where the transmission arrangement for each channel relies on the occurrence rates of denial-of-service (DoS) attacks. A sufficient condition is then proposed to guarantee the synchronization of MSNNs. Finally, an example is adopted to substantiate the efficiency of the obtained results.