the development of fundamental technologies that are instrumental in strengthening the security, Privacy and trustworthiness of decentralized artificial intelligence (AI)
Our Research Focus
The Private AI Collaborative Research Institute will focus its efforts on overcoming five main obstacles of the current centralized approach:
Training data is decentralized in isolated silos and often inaccessible.
Most data stored at the edge is privacy-sensitive and cannot be moved to the cloud.
Today’s solutions are insecure and require a single trusted data center.
Centralized training can be easily attacked by modifying data anywhere between collection and cloud. There is no framework for decentralized secure training among potentially untrusting participants.
Centralized models become obsolete quickly.
Infrequent batch cycles of collection, training, and deployment lead to outdated models, making continuous and differential retraining not possible.
Centralized compute resources are costly and throttled by communication and latency.
It requires vast data storage and compute as well as dedicated accelerators to make training viable.
Federated Machine Learning (FL) is limited.
While FL can access data at the edge, it cannot reliably guarantee privacy and security.
Principal Investigators
Technical University of Darmstadt Principal Investigator and Academic Coordinator: Ahmad-Reza Sadeghi
Universitiy of Waterloo Principal Investigator: N. Asokan and Florian Kerschbaum
University of Southern California Principal Investigators: Salman Avestimehr and Murali Annavaram
University of Wuerzburg Principal Investigator: Alexandra Dmitrienko
University of California, San Diego Principal Investigator: Farinaz Koushanfar
Université Catholique de Louvain Principal Investigators: Axel Legay and Thomas Given-Wilson
University of Toronto Principal Investigator: Nicolas Papernot
Technical University of Darmstadt Principal Investigator: Thomas Schneider
National University of Singapore Principal Investigator: Reza Shokri
Carnegie Mellon University Principal Investigator: Virginia Smith
The goal of the Private AI Collsborative Institute is to push the state of the art on decentralized and privacy-preserving machine learning. Read more here: