Biblio

Underwater Acoustic Networks (UANs) have long been recognized as an instrumental technology in various fields, from ocean monitoring to defense settings. Their security, though, has been scarcely investigated despite the strategic areas involved and the intrinsic vulnerability due to the broadcast nature of the wireless medium. In this work, we focus on attacks for which the attacker has partial or total knowledge of the network protocol stack. Our strategy uses a watchdog layer that allows upper layers to gather knowledge of overheard packets. In addition, a reputation system that is able to label nodes as trustful or suspicious is analyzed and evaluated via simulations. The proposed security mechanism has been implemented in the DESERT Underwater framework and a simulation study is conducted to validate the effectiveness of the proposed solution against resource exhaustion and sinkhole attacks.

Autonomous Underwater Vehicles (AUVs) have several fundamental civilian and military applications, and Denial of Service (DoS) attacks against their communications are a serious threat. In this work, we analyze such an attack using game theory in an asymmetric scenario, in which the node under attack does not know the position of the jammer that blocks its signals. The jammer has a dual objective, namely, disrupting communications and forcing the legitimate transmitter to spend more energy protecting its own transmissions. Our model shows that, if both nodes act rationally, the transmitter is able to quickly reduce its disadvantage, estimating the location of the jammer and responding optimally to the attack.

Security is one of the key aspects of underwater acoustic networks, due to the critical importance of the scenarios in which these networks can be employed. For example, attacks performed to military underwater networks or to assets deployed for tsunami prevention can lead to disastrous consequences. Nevertheless, countermeasures to possible network attacks have not been widely investigated so far. One way to identify possible attackers is by using reputation, where a node gains trust each time it exhibits a good behavior, and loses trust each time it behaves in a suspicious way. The first step for analyzing if a node is behaving in a good way is to inspect the network traffic, by detecting all conversations. This paper proposes both centralized and decentralized algorithms for performing this operation, either from the network or from the node perspective. While the former can be applied only in post processing, the latter can also be used in real time by each node, and so can be used for creating the trust value. To evaluate the algorithms, we used real experimental data acquired during the EDA RACUN project (Robust Underwater Communication in Underwater Networks).

Underwater acoustic communications experiments often involve custom implementations of schemes and protocols for the physical and data link layers. However, most commercial modems focus on providing reliable or optimized communication links, rather than on allowing low-level reconfiguration or reprogramming of modulation and coding schemes. As a result, the physical layer is typically provided as a closed, non-reprogrammable black box, accessible by the user only through a specific interface. While software-defined modems would be the ultimate solution to overcome this issue, having access to the symbols transmitted by the modems using a proprietary modulation format already opens up a number of research opportunities, e.g., aimed at the cross-layer design and optimization of channel coding schemes and communication protocols. In this paper, we take the latter approach. We consider the commercial EvoLogics modem, driven by a custom firmware version that bypasses the channel coding methods applied by the modem, and allows the user to set the transmit bit rate to any desired value within a given set. This makes it possible to evaluate different coding schemes in the presence of different bit rates. Our results show that the custom firmware offers sufficient flexibility to test different configurations of the coding schemes and bit rates, by providing direct access both to correctly decoded and to corrupted symbols, which can be separated at the receiver for further processing. In addition, we show that the DESERT Underwater framework can also leverage the same flexibility by employing low-level physical layer access in more complex networking experiments.