Abstract
The objective of this research work is to propose a new model of intrusion detection system for a fleet of UAVs deployed with an ad hoc communication architecture. The security of a drone fleet is rarely addressed by the scientific community, and most research has focused on routing protocols and battery autonomy, while ignoring the security aspect. The multi-agent paradigm is considered the most adequate and appropriate solution to model an effective intrusion detection system capable of detecting intrusions targeting a drone fleet. Multi-agent systems can perfectly address the security problem of a drone fleet, given the mobility, autonomy, cooperation and distribution characteristics present in the network linking the different nodes of the fleet. The proposed model consists of a set of cooperative, autonomous, communicating, learning and intelligent agents that collaborate with each other to carry out intrusion and suspicious activity detection missions that can target the network of a fleet of drones. Our system is autonomous and can detect known and unknown cyber attacks in real time without the need for human experts, who generally design the signatures of known attacks for conventional intrusion detection systems.
Highlights
Drones play a major role in the everyday life of individuals, given their extensive use in several areas of expertise, and will be the trend worldwide
The MAIS-IDS (Multi-agent Artificial Immune System - Intrusion Detection System) is a hybrid IDS by anomaly detection that is capable of analyzing system configurations to detect activities that may be real intrusions that threaten the security of the system
Step 4: Depending on the result of the matching verification, there are three possible scenarios: o Either the packet matches an attack signature already known by the knowledge base, in which case the Filtering Agent (FA) alerts the system administrator to see the intrusion details, o Either the network packet is normal and does not represent any risk for the fleet network and in this case the packet will be ignored and will not undergo any further processing, o And if the package is not recognized by the signature database, in this case it will be sent to the following agents to undergo the necessary treatments to identify its nature
Summary
Drones play a major role in the everyday life of individuals, given their extensive use in several areas of expertise, and will be the trend worldwide. A single drone cannot perform all the missions it is assigned, especially when it has to cover a large geographic area To overcome these limitations, a fleet of drones [3] is needed, which consists of connecting several drones via a network, so that they can cooperate and collaborate with each other to accomplish more complex tasks. The security issue is necessary for several reasons: Firstly, because the architecture of the Mobile Adhoc In light of these observations, it is necessary to ensure the security of a UAV network to detect intrusions that could affect the security principles summarized by the CIA triad (Confidentiality, Integrity and Authentication). Because of the absence of message and node authentication services, knowing that it is possible to inject forged packets into the network to disrupt the proper functioning of the routing algorithm This kind of attacks can corrupt the communication or decrease the network performance [7].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
