Project description
Cloud-based, platform-agnostic defence framework for AI applications
Malicious actions and adversarial attacks pose significant threats to AI applications and operations, making innovative solutions for AI protection critically necessary. The EU-funded cPAID project aims to research, design, and develop a cloud-based, platform-agnostic defence framework to safeguard AI applications and operations from these attacks. The project will address adversarial attacks such as poisoning and evasion by using AI-based defence methods and ensuring compliance with EU principles for AI ethics. In addition, the project will validate AI system performance in real-life scenarios and promote research to develop certification schemes that certify the robustness, security, privacy, and ethical excellence of AI applications and systems.
Objective
cPAID envisions researching, designing, and developing a cloud-based platform-agnostic defense framework for the holistic protection of AI applications and the overall AI operations of organizations against malicious actions and adversarial attacks. cPAID aims at tackling both poisoning and evasion adversarial attacks by combining AI-based defense methods (e.g. life-long semi-supervised reinforcement learning, transfer learning, feature reduction, adversarial training), security- and privacy-by-design, privacy-preserving, explainable AI (XAI), Generative AI, context-awareness as well as risk and vulnerability assessment and threat intelligence of AI systems. cPAID will identify guidelines to a) guarantee security- and privacy-by-design in the design and development of AI applications, b) thoroughly assess the robustness and resiliency of ML and DL algorithms against adversarial attacks, c) ensure that EU principles for AI ethics have been considered, and d) validate the performance of AI systems in real-life use case scenarios. The identified guidelines aspire to promote research toward developing certification schemes that will certify the robustness, security, privacy, and ethical excellence of AI applications and systems.
Fields of science
CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques.
CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques.
Programme(s)
Funding Scheme
HORIZON-RIA - HORIZON Research and Innovation ActionsCoordinator
8070 Bertrange
Luxembourg
See on map
Participants (17)
Legal entity other than a subcontractor which is affiliated or legally linked to a participant. The entity carries out work under the conditions laid down in the Grant Agreement, supplies goods or provides services for the action, but did not sign the Grant Agreement. A third party abides by the rules applicable to its related participant under the Grant Agreement with regard to eligibility of costs and control of expenditure.
176 71 Athina
See on map
041386 BUCURESTI
See on map
The organization defined itself as SME (small and medium-sized enterprise) at the time the Grant Agreement was signed.
02-326 WARSZAWA
See on map
3013 Limassol
See on map
The organization defined itself as SME (small and medium-sized enterprise) at the time the Grant Agreement was signed.
46022 Valencia
See on map
10612 Tallinn
See on map
The organization defined itself as SME (small and medium-sized enterprise) at the time the Grant Agreement was signed.
28050 MADRID
See on map
71004 Heraklion
See on map
71110 Irakleio
See on map
38106 Braunschweig
See on map
The organization defined itself as SME (small and medium-sized enterprise) at the time the Grant Agreement was signed.
1050 Bruxelles / Brussel
See on map
3071 Limassol
See on map
The organization defined itself as SME (small and medium-sized enterprise) at the time the Grant Agreement was signed.
714 14 GAZI
See on map
The organization defined itself as SME (small and medium-sized enterprise) at the time the Grant Agreement was signed.
A91 RW26 DUNDALK CO LOUTH
See on map
The organization defined itself as SME (small and medium-sized enterprise) at the time the Grant Agreement was signed.
7491 Trondheim
See on map
43124 Parma
See on map
1700 SOFIA
See on map
The organization defined itself as SME (small and medium-sized enterprise) at the time the Grant Agreement was signed.