The AIAS Project

AIAS is an EU funded research project which aims to design and develop an innovative AI-based security platform for the protection of AI systems’ technical robustness and AI-based operations of organisations. AIAS innovative approach relies on Adversarial AI defence methods, deception mechanisms and  explainable AI solutions that empower security teams to materialise the concepts of “AI for Cybersecurity” and “Cybersecurity for AI”.

AIAS Objectives

Holistic Protection

Conceptualize and develop a service architecture integrating AI-empowered applications, deception
mechanisms, and mitigation techniques towards the holistic protection of organizations against cyberattacks and
adversarial AI

Attack Scenarios

Design and develop a novel adversarial AI engine for creating attack scenarios tailored to the
characteristics of the targeted organisations’ hardware and software infrastructure

Novel Intelligent Deception Methods

Design and implement novel intelligent deception methods based on high-interaction honeypots, digital
twins, and virtual personas

AI-based Methods for Protection

Design, develop, and assess AI-based methods for the detection and mitigation of cyberattacks including
adversarial AI attacks as well as conceptualize and implement data collection and fusion methods

XAI-based Recommendation Engine

Develop and verify explainable AI (XAI)-based recommendation engine empowering human-in-the-loop
proactive decisions to thoroughly mitigate adversarial AI attacks

Real-life Usage

Assess the functionality, effectiveness and efficiency of AIAS in real-life scenarios

Recent News