Security and Safety for Shared AI by Deep Model Design

S3AI will provide the foundations required to build secure and save shared artificial intelligence systems: methods for privacy preservation, protection against adversarial attacks and guarantees for the system’s intended behavior.

S3AI Topics

Shared AI Theory

The theory part of S3AI comprises mathematical aspects of transfer learning and a novel computational geometric approach for deep model analysis:

Tessellation: study the interdependence between a deep model represented as neural network, its induced (tessellation) geometry in the input space and its separability properties;

Deep Transfer Learning: provide quantitative bounds on the misclassification and dertermine convergence rates in transfer learning settings;

Software Platform for Shared AI

A software platform for devloping and testing shared AI is envisoned that goes beyond standard federated learning by taking transfer learning into account:

Development Platform: to support the configuration, instantiation and orchestration of pipelines for training transfer learning and confidentiality preservation algorithms;

Test Environment: for modeling threat and attack scenarios to evaluate privacy and confidentiality protection and identify vulnerabilities;

Applications for Shared AI

S3AI takes up and bundles requirements from the companies, reflects them from the point of view of integrity and privacy threat scenarios, comprising:

Specification of requirements from the company partners’ application scenarios in terms of safety, information security and trust and elaboration of test scenarios for benchmark analysis;

Benchmark analysis regarding privacy and robustness against various threat scenarios and against standard deep learning models;

Guidelines for industrial partners as basis for R&D strategy development regarding the S3AI objectives;