Cyber-kinetic attacks using Artificial Intelligence

Informations projet

KINAITICS

N° de convention de subvention: 101070176

DOI

10.3030/101070176

Projet clôturé

Date de signature de la CE 20 Juin 2022

Date de début 1 Octobre 2022

Date de fin 30 Septembre 2025

Financé au titre de

• Civil Security for Society

Coût total

€ 4 030 723,75

Contribution de l’UE

€ 4 030 723,75

Coordonné par

COMMISSARIAT A L ENERGIE ATOMIQUE ET AUX ENERGIES ALTERNATIVES
France

CORDIS fournit des liens vers les livrables publics et les publications des projets HORIZON.

Les liens vers les livrables et les publications des projets du 7e PC, ainsi que les liens vers certains types de résultats spécifiques tels que les jeux de données et les logiciels, sont récupérés dynamiquement sur OpenAIRE .

Livrables

Documents, reports (4)

Communication actions M6

This deliverable will provide a detailed description of the actions taken to communicate about the project. Incremental versions of the document will be delivered, at M6, M18 and M36. Document at M6 will mainly describe communication plans. At M18, it will report on the past actions and describe the updated version of the communication actions. At M36, the deliverable will focus on reporting and assessing the communication actions taken during the project.

Dissemination and exploitation plans M24

These deliverables will provide a plan for dissemination and exploitation activities which will be implemented in T7.2. Plans will identify the project assets to communicate and exploit, the targets for the dissemination and exploitation activities, as well as the actions more suitable to reach them. It will also set interim and final KPIs for both activities to ensure project goals are fully achieved.

Dissemination and exploitation plans M12

These deliverables will provide a plan for dissemination and exploitation activities which will be implemented in T7.2. Plans will identify the project assets to communicate and exploit, the targets for the dissemination and exploitation activities, as well as the actions more suitable to reach them. It will also set interim and final KPIs for both activities to ensure project goals are fully achieved.

Communication actions 18

This deliverable will provide a detailed description of the actions taken to communicate about the project. Incremental versions of the document will be delivered, at M6, M18 and M36. Document at M6 will mainly describe communication plans. At M18, it will report on the past actions and describe the updated version of the communication actions. At M36, the deliverable will focus on reporting and assessing the communication actions taken during the project.

Publications

Conference proceedings (6)

How to Train your Antivirus: RL-based Hardening through the Problem Space

Auteurs: Ilias Tsingenopoulos, Jacopo Cortellazzi, Branislav Bošanský, Simone Aonzo, Davy Preuveneers, Wouter Joosen, Fabio Pierazzi, Lorenzo Cavallaro
Publié dans: The 27th International Symposium on Research in Attacks, Intrusions and Defenses, 2025
Éditeur: ACM
DOI: 10.1145/3678890.3678912

KINAITICS: Enhancing Cybersecurity Education Using AI-Based Tools and Gamification

Auteurs: Francesco Zola, Xabier Echeberria, Jokin Petisco, Nikos Vakakis, Antonis Voulgaridis, Kostantinos Votis
Publié dans: Proceedings of the 2024 16th International Conference on Education Technology and Computers, 2025
Éditeur: ACM
DOI: 10.1145/3702163.3702183

NeuralSentinel: Safeguarding Neural Network Reliability and Trustworthiness

Auteurs: Xabier Echeberria-Barrio, Mikel Gorricho, Selene Valencia, Francesco Zola
Publié dans: Computer Science & Information Technology (CS & IT), Numéro 2, 2024, ISSN 2231-5403
Éditeur: AIRCC
DOI: 10.5121/csit.2024.140209

Designing AI Systems with Correction Mechanisms Towards Attack-Resilient Architectures

Auteurs: Efi Kafali, Christoforos N. Spartalis, Theodoros Semertzidis, Charalampos Z. Patrikakis, Petros Daras
Publié dans: 2025 IEEE International Conference on Cyber Security and Resilience (CSR), 2025
Éditeur: IEEE
DOI: 10.1109/CSR64739.2025.11130000

CYBERSHIELD: A Competitive Simulation Environment for Training AI in Cybersecurity

Auteurs: José Álvaro Fernández Carrasco, Iñigo Amonarriz Pagola, Raúl Orduna Urrutia, Rodrigo Román
Publié dans: 2024 11th International Conference on Internet of Things: Systems, Management and Security (IOTSMS), 2024
Éditeur: IEEE
DOI: 10.1109/IOTSMS62296.2024.10710208

Building a Use Case-Driven Adversarial Threat Matrix: A Comprehensive Approach

Auteurs: Prodromos Kiriakidis, Efi Kafali, Georgios Rizos, Antonis Voulgaridis, Theodoros Semertzidis, Stephane Gazut, Petros Daras, Konstantinos Votis
Publié dans: 2024 IEEE International Conference on Cyber Security and Resilience (CSR), 2024
Éditeur: IEEE
DOI: 10.1109/CSR61664.2024.10679406

Peer reviewed articles (3)

Defending Against AI Threats with a User-Centric Trustworthiness Assessment Framework

Auteurs: Efi Kafali; Davy Preuveneers; Theodoros Semertzidis; Petros Daras
Publié dans: Big Data and Cognitive Computing, 2024, ISSN 2504-2289
Éditeur: MDPI
DOI: 10.3390/BDCC8110142

Dynamic Trade-Offs in Adversarial Training: Exploring Efficiency, Robustness, Forgetting, and Interpretability

Auteurs: Efi Kafali, Theodoros Semertzidis, Petros Daras
Publié dans: Neural Processing Letters, Numéro 57, 2025, ISSN 1573-773X
Éditeur: Springer Science and Business Media LLC
DOI: 10.1007/S11063-025-11751-Z

An Ontology-Based Cybersecurity Framework for AI-Enabled Systems and Applications. Future Internet. 2024; 16(3):69.

Auteurs: Preuveneers D, Joosen W.
Publié dans: Future Internet, Numéro 69, 2024, ISSN 1999-5903
Éditeur: MDPI
DOI: 10.3390/fi16030069