Project Details
Description
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.
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.
| Short title or EU acronym | cPAID |
|---|---|
| Acronym | EUAR200 |
| Status | Active |
| Effective start/end date | 1/10/24 → 30/09/27 |
Keywords
- Cybersecurity Research Domains
- AI
- Security
Flemish discipline codes in use since 2023
- Artificial intelligence not elsewhere classified