Striking Developments : WP3 Outcomes and Growth

Use case 2 (Increased Cybersecurity situation awareness for efficient threat mitigation), led by Albert Calvo lbanez, is tasked with building a comprehensive tool pipeline for cybersecurity. The pipeline will encompass various essential components aimed at enhancing the security measures and efficiency of cybersecurity operations. The following tools are to be included in the pipeline:

Dataset Selection : Identifying and selecting appropriate datasets for analysis and training purposes.

Feature Augmentation : Enhancing the features of datasets to improve the performance of machine learning algorithms.

Constrained ML : Implementing machine learning algorithms with constraints to optimize performance under specific conditions.

Explainability : Incorporating mechanisms to explain the decisions made by machine learning models.

Visualization : Developing visual representations to aid in the interpretation of data and results.

Knowledge Management Module : Implementing a module, potentially based on Zenoh, for managing and sharing knowledge across the pipeline. 

TUDelft, Bournemouth University, UPC, and Athenarc will build upon this benchmark, implementing their tools to improve specific aspects.

I2CAT partner, will prepare a mini-benchmark for use case 2 using the private phishing dataset. This benchmark will involve a series of scripts or a full notebook, incorporating cross-validation and testing processes in addition to the assessment of all various data processing, feature selection and augmentation methods. This benchmark also will help the evaluation of different ML classification algorithms, with tuning and selection. The development process will emphasize on the collaboration and rapid prototyping, with all WP3 partners actively engaged.

Overall, the pipeline development process will be characterized by collaborative, rapid prototyping, with active involvement from all WP3 partners to ensure the success and effectiveness of the tools.

The ExtremeXP project is co-funded by the European Union Horizon Program HORIZON-CL4-2022-DATA-01-01, under Grant Agreement No. 101093164
© ExtremeXP 2023. All Rights Reserved – Privacy Policy
Verified by MonsterInsights