In AI4PublicPolicy, the CRISP-DM methodology was leveraged to define the policy models to be used in policy development, along with dataset models, treating Policy as an AI problem. The Policy Model that was designed for Ai4PublicPolicy consists of attributes and related entities representing: - Problem understanding -...

In our previous blog post, the methodology and the process applied by the project pilots to define the datasets were outlined. In this blog post, we present a UML (Unified Modeling Language) model constructed from the data collected from the pilots' provided data sources. To begin,...

In order for the AI4PublicPolicy pilots to build policy models, it has been necessary to collect and analyse specific datasets from their available data sources. In this blog, we outline the methodology and the process applied by the project pilots to define such datasets. The data...

Part 2 – Architecture and Procedures In the first part of our blog series on the Policy Extraction and Recommendation toolkit developed for the AI4PublicPolicy platform, we discussed the design goals. In this second part, we delve into the architecture of the module. After analyzing state-of-the-art solutions,...

Part 1 – Solution Design The AI4PublicPolicy Policy Extraction and Recommendation module provides the tools required for the creation of an AI pipeline. The trained and tested AI models delivered through this pipeline allow the policymakers to design an appropriate policy. The design of the module has...

The Strategy Defence Library is one of the main components of the AI Security Toolbox inside the AI4PublicPolicy platform. It hosts state-of-the-art solutions against the most common and effective adversarial attacks. The Strategy Defence Library includes the best algorithms used for AI Adversarial Defence; and...

In the first part of our blog on Adversarial AI Defences, we introduced their generic categories. To tailor our suggestions to each AI4PublicPolicy use case and model, we've created the following table outlining the most promising and effective defences. This table includes the names of specific...

In our previous blog, in the context of securing machine learning, we conducted an in-depth analysis of Adversarial AI & Attacks. In this two-part blog series, our attention turns to the examination of Adversarial Defences. While early work in machine learning has often assumed a closed...

On November 15th and 16th, the AI4PublicPolicy project conducted an online consortium meeting dedicated to monitoring and assessing the integration of VPME solutions and tools to the project’s pilot sites. The meeting constituted a structured internal validation activity for the delivered AI-based functionalities of the...

Nicosia Municipality's 4th co-creation workshop took place on December 4th, 2023, at the central building offices of the Municipality. The workshop aimed to present the progress of the Nicosia pilot and the proposed solutions to stakeholder groups, users, civilians, and technicians, and to gather feedback...