Dissemination

The AIAS consortium is proud to announce the completion of Deliverable D3.1 – “AIAS Deception Layer”, a major milestone that advances both the research and implementation of deception-based protection mechanisms for Artificial Intelligence (AI) systems. This deliverable represents a comprehensive effort combining state-of-the-art research, engineering design, and proof-of-concept implementations to strengthen the resilience of AI-driven […]

The AIAS project continues to strengthen its scientific and technological impact with the publication of three new peer-reviewed research papers, presented at leading international conferences and addressing critical challenges at the intersection of artificial intelligence, cybersecurity, and resilient digital infrastructures. Together, these publications reflect the AIAS vision of advancing secure, trustworthy, and resilient AI-enabled systems,

The AIAS project is pleased to announce the release of its 2nd official brochure, now available not only in English, but also fully translated into Greek, Spanish, and Romanian. Check our communication material page for more information. This new edition highlights the project’s latest achievements, ongoing technical developments, and the growing collaboration across partners as

Our research article “Testing the limits: exploring adversarial techniques in AI models”, authored by Apostolis Zarras, Athanasia Kollarou, Aristeidis Farao, Panagiotis Bountakas, and Christos Xenakis, has been published in PeerJ Computer Science and was proudly supported by the AIAS project. As Artificial Intelligence increasingly permeates critical domains such as healthcare, finance, and autonomous systems, the

We are pleased to announce our latest publication in the prestigious Q1-ranked journal Array (Elsevier) with title: From Vulnerability to Resilience: Adversarial Training and Real-Time Detection for AI Security As Artificial Intelligence becomes a foundational component across critical domains—such as cybersecurity, healthcare, finance, and smart infrastructures—the need to safeguard AI models against adversarial threats is