In this interview, you will find Edgardo Montes de Oca, from Montimage, explaining use case 2.
This particular use case aims to evaluate the proposed guidelines and techniques concerning the explainability, resiliency, and distribution of AI/ML techniques. The evaluation will focus on the techniques currently employed by MI within its MMT monitoring framework for cybersecurity analysis and protection of 5G and IoT networks, encrypted traffic analysis, and root cause analysis (RCA). The objective is to determine how the outcomes of the SPATIAL project can enhance the transparency, resilience against adversarial ML, precision (such as through the combination of multiple ML algorithms), and efficiency (such as leveraging distributed data and ML processing) of the existing or newly introduced techniques. To assess accountability and resilience, defined metrics will be employed to validate their relevance and applicability, followed by measuring the achieved improvements. MI will contribute a testbed pilot to deploy and evaluate the enhanced techniques. Specific validation scenarios will be defined and implemented accordingly.
The results of SPATIAL will be of great importance in improving these techniques, particularly concerning the use, resiliency, explainability and assessment of AI/ML. Techniques, guidelines and building blocks developed by the SPATIAL project will be considered and evaluated with respect to the improvements in the performance, transparency and precision they bring to the security analysis and algorithms. You can read more about the use cases here.
Watch the interview!