It has been demonstrated that the AIS initially set for security purposes, suffers from errors, falsifications and spoofing cases ([1] and [2]) A system for alert triggering based on AIS messages treatment and behavioural analysis has been set. This system is made of several modules [3], one for data storage, one for data analysis (with archived data or on-the-fly) and another one for scenario assessment leading to risk evaluation and alert triggering. We propose a method taking into consideration the complex structure of AIS messages[4], in which each message data quality and integrity is assessed with respect to AIS specifications, other messages (either sent by the same vessel or not) and some environmental data (such as fleet registers). A set of selected scenarios have been implemented (such as identity theft, whereabouts spoofing, vessel disappearance) and are assessed subsequently. Those scenarios are linked to risks of maritime navigation such as collisions, illegal trade or terrorism, the analysis of which, in conjunction with the vessel environment, leading to the assignment of levels of alert corresponding to the risks defined, suitable to be handed to relevant authorities as decision support information. References: [1] Ray C., Iphar C., Napoli A., Gallen R. and Bouju A.,DeAIS project: Detection of AIS Spoofing and Resulting Risks. In: proceedings of OCEANS 2015, 18-21 May 2015; [2] Balduzzi M., Pasta A. and Wilhoit K., A security evaluation of AIS automated identification system. In: proceedings of ACSAC 2014, 7-12 December 2014; [3] Iphar C., Napoli A. and Ray C., Integrity Assessment of a Worldwide Maritime Tracking System for a Geospatial Risk Analysis at Sea. In: proceedings of the 20th AGILE Conference, 9-12 May 2017; [4] Tunaley J.K.E., Utility of Various AIS Messages for Maritime Awareness. In: Proceedings of the 9th Advanced SAR Workshop. 15-18 October 2013.< Réduire