Year: 2014
Type: dissertation
Abstract: Aeronautics is actually facing a confluence of events: connectivity of aircraft is gradually increasing in order to ease the air traffic management and aircraft fleet maintainability, and to offer new services to passengers while reducing costs. The core avionics functions are thus linked to what we call the Open World, i.e. the non-critical network of an aircraft as well as the air traffic services on the ground. Such recent evolutions could be an open door to cyber-attacks as their complexity keeps growing. However, even if security standards are still under construction, aeronautical certification authorities already require that aircraft manufacturers identify risks and ensure aircraft will remain in a safe and secure state even under threat conditions. To answer this industrial problematic, this thesis first proposes a simple semi-quantitative risk assessment framework to identify threats, assets and vulnerabilities, and then rank risk levels according to threat scenario safety impact on the aircraft and their potential likelihood by using adjustable attribute tables. Then, in order to ensure the aircraft performs securely and safely all along its life-cycle, our second contribution consists in a generic and autonomous network monitoring function for intrusion detection based on Machine Learning algorithms. Different building block options to compose this monitoring function are proposed such as: two ways of modeling the network traffic through characteristic attributes, two Machine Learning techniques for anomaly detection: a supervised one based on the One Class Support Vector Machine algorithm requiring a prior training phase and an unsupervised one based on subspace clustering. Since a very common issue in anomaly detection techniques is the presence of false alarms, we prone the use of the Local Outlier Factor (a density indicator) to set a threshold in order to distinguish real anomalies from false positives. This thesis summarizes the work performed under the CIFRE (Convention Industrielle de Formation par la Recherche) fellowship between THALES Avionics and the CNRS-LAAS at Toulouse, France.
Source: theses.fr (ABES)
Author: Gil Casals, Silvia
Language: English
Subfield: Computer Networks and Communications
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2592847794