SPADE: Secure Privacy-preserving Analytics in Distributed Environments

Data drives progress in AI, health, and digital services, but centralizing sensitive information creates single points of failure vulnerable to breaches and misuse. SPADE develops cryptographic methods that enable privacy-preserving data analytics without centralization. The project builds on secure multiparty computation, which allows parties to jointly analyze distributed data without exposing raw inputs, and differential privacy, which protects against information leakage from outputs. Together, these technologies will form new theoretical foundations for scalable, secure, and private data analytics. SPADE focuses on advancing efficiency and robustness of these methods, ensuring they can handle large-scale analytics and resist future threats such as quantum attacks. By emphasizing foundational research, SPADE aims to deliver breakthroughs in cryptography and algorithms that will strengthen Denmark’s international leadership in privacy-preserving technologies.