The SOLAS convention created an electronic system of message broadcasting between vessels: the Automatic Identification System (AIS). Albeit initially designed for security purposes, some people use the system another way, such as fleet surveillance, and the system suffers from errors, falsifications and spoofing. AIS data structure is complex, with 27 different messages, each one having a given number of data fields with various size, importance and type [1]. We propose a method based on the data quality dimensions and particularly the integrity of data within the message to assess the confidence in each message received, with a data processing done both on-the-fly with coming data and when data is stored in the database for comparison with archived data [2] and signal-based assessment we propose [3]. Each message will be assigned a confidence coefficient based on the processing of a checklist of ad-hoc items. The purpose is to assign a grade of alert and a level of associated risks (such as boarding, pollution, terrorism) to each message, group of messages sent by the same vessel or situation, suitable to be given for further studies to relevant authorities such as coast guards or MRCCs. References: [1] Tunaley, 2013. Utility of Various AIS Messages for Maritime Awareness. In proceedings of the 9th ASAR Workshop. Longueuil, Canada, October 2013. [2] Iphar, Napoli et Ray, 2016. Risk Analysis of falsified Automatic Identification System for the improvement of maritime traffic safety. In proceedings of the ESREL 2016 conference, Glasgow, United Kingdom, September 2016. [3] Alincourt, Ray, Ricordel, Dare-Emzivat et Boudraa, 2016. Methodology for AIS Signature Identification through Magnitude and Temporal Characterization. In proceedings of the OCEANS’16 SHANGHAI conference, Shanghai, China, April 2016.< Réduire