On November 13, 2025, the first edition of LLM4Sec, the Workshop on the Use of Large Language Models for Cybersecurity, took place in Washington, DC, USA. Organized by Antonino Rullo (ICAR), Giuseppe Manco (ICAR), and Luca Caviglione (IMATI), LLM4Sec aims…
Abstract The HumanE AI Net brings together top European research centers, universities and key industrial champions into a network of centers of excellence that goes beyond a narrow definition of AI and combines world leading AI competence with key players…
WHAM! recognizes the increasingly important role of the Machine Learning-as-a-service (MLaaS) paradigm, which delegates most of the training pipeline to third parties. In this new context, traditional security assessment techniques covered by Adversarial ML (poisoning, evasion, inversion, or pattern mining…
CyberSec4Europe's main objective is to pilot the consolidation and projection into the future of European-wide cybersecurity capabilities required to secure and maintain a European democracy and a world leading digital econ-omy. CyberSec4Europe has translated this broad objective into measurable, concrete…
Abstract The project aims to develop new methodologies, techniques, and software solutions capable of enabling Blockchain technologies in the fields of privacy, the sharing economy, and digital rights. Specifically, in the area of privacy, the goal is to study and…
The Humane AI Flagship will develop the scientific foundations and technological breakthroughs needed to shape the ongoing artificial intelligence (AI) revolution. The goal is to design and deploy AI systems that enhance human capabilities and empower people -- both as…
The project aimed to define new methodologies, techniques, architectures, and software solutions based on Artificial Intelligence and Machine Learning capable of playing an enabling role in the creation of an analysis and prediction platform for customer engagement and satisfaction. The…
Project: Securing Containers (SecCo) Operating Systems (OS) and Virtualization Technologies (VT) are key enablers for existing and emerging computation and communication paradigms, namely cloud, fog, edge computing and 5G/6G. By leveraging the primitive security mechanisms provided by the hardware, OS and…
This activity aims to design and develop innovative solutions to identify and manage information disorder threats that come alive through fake news and deep fake spreading. These malicious actions, leveraging people’s cognitive bias, generate citizens’ disapproval and media and institutions…
