AIAS project conducts online training on adversarial AI/ML attacks

On February 27, the University of Malaga organized an online training event dedicated to the study of adversarial attacks targeting Artificial Intelligence (AI) and Machine Learning (ML) models. The session focused on presenting key research outcomes developed within the framework of the AIAS MSCA project, particularly those reported in Deliverable 3.2: “Taxonomy of Adversarial AI […]

AIAS project conducts online training on adversarial AI/ML attacks Read More »

Presentation of the AIAS project in the German-Romanian Chamber of Commerce and Industry (AHK Romania) 

The AIAS Project was represented by partners BEIA and UPRC on March 3rd, 2026, at the event “The Energy That Makes Us Stronger”, organized by the German-Romanian Chamber of Commerce and Industry (AHK Romania). The event took place at the InterContinental Athénée Palace in Bucharest and gathered representatives of member companies, invited guests, and media.

Presentation of the AIAS project in the German-Romanian Chamber of Commerce and Industry (AHK Romania)  Read More »

New secondment in the context of the AIAS project

Dr. Michail Bampatsikos, a postdoctoral researcher from the University of Piraeus, started his secondment, in the context of the AIAS project, on 2 March 2026 in BEIA, an SME located in Bucharest, Romania. During his secondment, Michail will be involved in WP3/4/5 activities, specifically focusing on the design and delivery of the weaponizer responsible for executing

New secondment in the context of the AIAS project Read More »

AIAS Deliverable D3.2 Released: Advancing Knowledge on Adversarial AI Attacks

The AIAS consortium is pleased to announce the completion of Deliverable D3.2 – “Taxonomy of Adversarial AI Attacks”, developed under Task 3.3. This deliverable represents a significant step forward in understanding and systematically organizing the rapidly evolving landscape of adversarial threats targeting Artificial Intelligence and Machine Learning systems. Building a Comprehensive View of Adversarial AI

AIAS Deliverable D3.2 Released: Advancing Knowledge on Adversarial AI Attacks Read More »

AIAS Deliverable D3.1 Released: Introducing the AIAS Deception Layer for AI System Protection

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

AIAS Deliverable D3.1 Released: Introducing the AIAS Deception Layer for AI System Protection Read More »

Ongoing Secondment at BEIA Romania Strengthens AIAS Technical Development

The AIAS project continues to advance its research and innovation objectives through active collaboration and researcher mobility across consortium partners. In this framework, Anastassis Voudouris from UPRC is currently undertaking a one (1) month secondment at BEIA, an SME based in Bucharest, Romania. The secondment commenced on 26 January 2026 and is scheduled to conclude

Ongoing Secondment at BEIA Romania Strengthens AIAS Technical Development Read More »

 AIAS in 3rd multidisciplinary event “Current Public Health Topics”

Prof. Christos Xenakis from UPRC participated in the panel of the National Public Health Organization during the 3rd multidisciplinary event “Current Public Health Topics”, held on 17 December 2025 at the Agricultural University of Athens. He joined the session focusing on the security challenges emerging from the digitization of health services—from electronic health records and

 AIAS in 3rd multidisciplinary event “Current Public Health Topics” Read More »

AIAS site icon

AIAS Newsletter – Issue 5 Now Available

The 5th issue of the AIAS Newsletter (December 2025) has been published and is now available on the AIAS website. This edition presents recent progress and key developments of the AIAS project, including research advances in adversarial AI, updates on the AIAS architecture and core components, recent scientific publications, participation in international events, and an

AIAS Newsletter – Issue 5 Now Available Read More »

AIAS Advances Trustworthy and Secure AI Through Three New Scientific Publications

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,

AIAS Advances Trustworthy and Secure AI Through Three New Scientific Publications Read More »

AIAS at Open Conf 2025: Exploring Trust and Threats in AI-Driven Cybersecurity

AIAS was represented at Open Conf 2025, where Prof. Christos Xenakis moderated the panel “Agents of Trust, Agents of Threat”, focusing on the dual role of AI agents in contemporary cybersecurity. The panel discussion examined both the opportunities and the risks introduced by AI-driven agents, underscoring the need for robust, trustworthy, and secure AI systems.

AIAS at Open Conf 2025: Exploring Trust and Threats in AI-Driven Cybersecurity Read More »