cPAID

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, 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 identifies 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.

The objectives of the project are:

• To integrate DevPrivSecOps and MLOps to deliver the MLPrivSecOps methodology, including security-, privacy-, and robustness-by-design techniques along with adversarial attack mitigation methods.
• To adopts XAI techniques to help ML developers and engineers select appropriate algorithms to boost the resiliency of AI systems.
• To use SBOM techniques to increase AI software supply chain security.
• Combine Generative AI models with a taxonomy of existing adversarial attacks to explore the application of GenAI for generating synthetic adversarial attacks.
• Deliver a meta-SIEM that will enhance the capabilities of traditional SIEMS by adopting anomaly detection, event management, and visualization using novel unsupervised and XAI methods.