Cyber-kinetic attacks using Artificial Intelligence

Leistungen

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.

Final report on the ethical, legal and privacy framework, including technology assessment and DPIA

The deliverable will provide the components of specific Guidelines, both technical and operational, and best practices in order to handle AI attacks and to use AI for cybersecurity defence in a way that complies with the legal obligations identified. This will include a DPIA of the solutions pre-deployment.

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.

Dissemination and exploitation plans M36

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.

Communication actions M36

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.

Veröffentlichungen

On Adaptive Decision-Based Attacks and Defenses

Autoren: Ilias Tsingenopoulos, Vera Rimmer, Davy Preuveneers, Fabio Pierazzi, Lorenzo Cavallaro, Wouter Joosen
Herausgeber: IEEE

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

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

Enhancing Bot Detection With Causally and Temporally Constrained Counterfactual Examples for Targeted Retraining

Autoren: Davy Preuveneers, Wouter Joosen
Herausgeber: IEEE

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

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

NeuralSentinel: Safeguarding Neural Network Reliability and Trustworthiness

Autoren: Xabier Echeberria-Barrio, Mikel Gorricho, Selene Valencia, Francesco Zola
Veröffentlicht in: Computer Science & Information Technology (CS & IT), Ausgabe 2, 2024, ISSN 2231-5403
Herausgeber: AIRCC
DOI: 10.5121/csit.2024.140209

The Adaptive Arms Race: Redefining Robustness in AI Security

Autoren: Ilias Tsingenopoulos, Vera Rimmer, Fabio Pierazzi, Lorenzo Cavallaro, Wouter Joosen,
Herausgeber: IEEE
DOI: 10.48550/ARXIV.2312.13435

Designing AI Systems with Correction Mechanisms Towards Attack-Resilient Architectures

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

CYBERSHIELD: A Competitive Simulation Environment for Training AI in Cybersecurity

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

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

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

Balancing Security and Privacy: Web Bot Detection, Privacy Challenges, and Regulatory Compliance under the GDPR and AI Act

Autoren: Javier Martínez Llamas Orcid , Koen Vranckaert , Davy Preuveneers Orcid , Wouter Joosen
Veröffentlicht in: Open Research Europe, ISSN 2732-5121
Herausgeber: F1000 Research Limited on behalf of the European Commission
DOI: 10.12688/OPENRESEUROPE.19347.1

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

Autoren: Efi Kafali; Davy Preuveneers; Theodoros Semertzidis; Petros Daras
Veröffentlicht in: Big Data and Cognitive Computing, 2024, ISSN 2504-2289
Herausgeber: MDPI
DOI: 10.3390/BDCC8110142

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

Autoren: Efi Kafali, Theodoros Semertzidis, Petros Daras
Veröffentlicht in: Neural Processing Letters, Ausgabe 57, 2025, ISSN 1573-773X
Herausgeber: 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.

Autoren: Preuveneers D, Joosen W.
Veröffentlicht in: Future Internet, Ausgabe 69, 2024, ISSN 1999-5903
Herausgeber: MDPI
DOI: 10.3390/fi16030069

Leistungen

Veröffentlichungen

Diese Seite teilen Diese Seite in sozialen Netzwerken teilen

Herunterladen Den Inhalt der Seite herunterladen