Strategic learning-based approaches for secure deployment of swarm of UAVs in IoT networks
Flores Cabezas, Xavier Alejandro (2022-06-14)
Flores Cabezas, Xavier Alejandro
X. Flores Cabezas
14.06.2022
© 2022 Xavier Alejandro Flores Cabezas. Ellei toisin mainita, uudelleenkäyttö on sallittu Creative Commons Attribution 4.0 International (CC-BY 4.0) -lisenssillä (https://creativecommons.org/licenses/by/4.0/). Uudelleenkäyttö on sallittua edellyttäen, että lähde mainitaan asianmukaisesti ja mahdolliset muutokset merkitään. Sellaisten osien käyttö tai jäljentäminen, jotka eivät ole tekijän tai tekijöiden omaisuutta, saattaa edellyttää lupaa suoraan asianomaisilta oikeudenhaltijoilta.
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:oulu-202206142819
https://urn.fi/URN:NBN:fi:oulu-202206142819
Tiivistelmä
In next generation wireless networks such as 5G and 6G, security is a key concern, for which physical layer security (PLS) emerges as an interesting solution which allows the provisioning of security to low-complexity devices. This work investigates the employment of unmanned aerial vehicles (UAVs) for providing secure transmissions in ground networks relying on information-theoretic security in internet of things (IoT) settings. To this goal, two scenarios are investigated, namely secure communications with UAVs as friendly jammers and secure communications in massive IoT networks served by a swarm of UAVs. For the former scenario, it is considered that two UAVs are deployed to act as friendly jammers to improve the secrecy in the communication between a pair of legitimate nodes in the presence of an eavesdropper of unknown location. For this scenario reinforcement learning techniques are leveraged for 3D positioning of UAVs in order to improve the secrecy performance of the system via friendly jamming. For the second scenario, it is considered that a set of UAVs acting as aerial base stations provide secure connectivity between the network and multiple ground nodes. Therein, both the association of the nodes and the 3D positioning of the UAVs are obtained by leveraging game theoretic tools and greedy algorithms with the goal of improving the secrecy of the system. In both scenarios, it is shown that the proposed solutions enhance the secrecy performance of the systems. Namely, in the first scenario it was shown that the proposed solution enhanced the secrecy of the system through friendly jamming, and in the second scenario it was found that game-theoretic approaches in both association of the IoT nodes and positioning of the UAVs presents a remarkable increase in secrecy performance over a random positioning, strongest channel association benchmark.
Kokoelmat
- Avoin saatavuus [32023]