AUTHOR=Mertens J. S. , Panebianco A. , Surudhi A. , Prabagarane N. , Galluccio L. TITLE=Network intelligence vs. jamming in underwater networks: how learning can cope with misbehavior JOURNAL=Frontiers in Communications and Networks VOLUME=4 YEAR=2023 URL=https://www.frontiersin.org/journals/communications-and-networks/articles/10.3389/frcmn.2023.1179626 DOI=10.3389/frcmn.2023.1179626 ISSN=2673-530X ABSTRACT=

In this paper, we present a machine-learning technique to counteract jamming attacks in underwater networks. Indeed, this is relevant in security applications where sensor devices are located in critical regions, for example, in the case of national border surveillance or for identifying any unauthorized intrusion. To this aim, a multi-hop routing protocol that relies on the exploitation of a Q-learning methodology is presented with a focus on increasing reliability in data communication and network lifetime. Performance results assess the effectiveness of the proposed solution as compared to other efficient state-of-the-art approaches.