Tommaso Puccetti and Lorenzo Sarti (UNIFI-CINI) spent their one-month secondment at Universidade Estadual de Campinas, Brazil.

The activities carried out concern the evaluation of the robustness of a Visual Odometry system that entrusts the calculation of the position to two ML models: SuperGlue and SuperPoint.

To evaluate the system's robustness, a failure injection campaign was carried out on the vehicle's camera, simulating failures that can occur on its lens.

The picture below is from the seminar taken by Lorenzo and Tommaso regarding the results collected through the failure injection campaign, and proposals of the research roadmap for future collaborations.

The work carried out lays the foundations for a more extensive experimental campaign that could also include an additional system that combines the above-mentioned VO system with a component based on IMU sensors.

Furthermore, the long-term goal will be to test possible mitigations that can increase the robustness of the models against this type of failure. The first proposal is to evaluate the use of Self Supervised Learning techniques.

In this period, also Prof. Andrea Ceccarelli (UNIFI-CINI) was seconded for two weeks at UNICAMP, to guide and support Tommaso and Lorenzo in their activities.

José Fonseca (University of Coimbra – UC/PT) spent his secondment at ResilTech in Pontedera, Italy. 

After discussions with researchers from ResilTech, they identified that data from the ICT Gateway application, which was one of the results of the NET2DG European project, is a good candidate to test the development of a new anomaly-based Intrusion Detection System (IDS) for databases. The ultimate goal is to the deployment of the Intrusion Detection System (IDS) in the ICT Gateway setup in order to increase the security of the ICT Gateway related with SQL injection-based attacks.

He gave a seminal that focused on the topic of the anomaly detection intrusion detection system for databases. It focused on the research problem, the proposed anomaly IDS for databases that have two levels for the definition of profiles, the experimental setup, including the ICT Gateway, and future work.

Francesco Mariotti and Francesco Terrosi (UNIFI-CINI) are currently seconded at INPE. They will work, respectively, on the BEDCS use case for i) creating a stochastic model for performability analysis and ii) analyzing anomalies in data received from collecting platforms. In the meantime, Prof. Andrea Bondavalli (UNIFI-CINI) has also been seconded at INPE for a period of two weeks. During the WETE workshop located at INPE, he gave a lecture titled "Dependability Challenges in Safety-Critical Systems: the adoption of Machine Learning" and a speech on Cyber Physical Systems and ADVANCE Project.

Francesco Mariotti and Francesco Terrosi (UNIFI-CINI) just ended their one-month secondment at INPE. They started to work on the BEDCS use case, with particular interest to the communication between Data Collecting Platforms (DCPs) and satellites, to support the creation of an orbit simulator (also suitable for constellations of satellites) and to investigate anomalies in data sent by DCPs.

 

On 4th of November, Antonio Bertachini Prado (INPE) concluded his secondment at UNIFI. In this period he worked on simulations of satellites' orbits, providing UNIFI group with new knowledge on this field of research and contributing to the BEDCS use case activities.