Practical, Private Assurance of the Value of Collaboration via Fully Homomorphic Encryption
This work addresses the need for secure and efficient pre-collaboration assurance in machine learning, particularly for parties with sensitive data, though it is incremental as it builds on existing FHE and differential privacy techniques.
The authors tackled the problem of enabling two parties to privately assess the value of collaboration on their datasets before sharing them, by developing an interactive protocol using fully homomorphic encryption and label differential privacy for neural networks. They achieved a significant speedup, with experiments showing the output accuracy obtained many orders of magnitude faster than using entirely FHE operations.
Two parties wish to collaborate on their datasets. However, before they reveal their datasets to each other, the parties want to have the guarantee that the collaboration would be fruitful. We look at this problem from the point of view of machine learning, where one party is promised an improvement on its prediction model by incorporating data from the other party. The parties would only wish to collaborate further if the updated model shows an improvement in accuracy. Before this is ascertained, the two parties would not want to disclose their models and datasets. In this work, we construct an interactive protocol for this problem based on the fully homomorphic encryption scheme over the Torus (TFHE) and label differential privacy, where the underlying machine learning model is a neural network. Label differential privacy is used to ensure that computations are not done entirely in the encrypted domain, which is a significant bottleneck for neural network training according to the current state-of-the-art FHE implementations. We formally prove the security of our scheme assuming honest-but-curious parties, but where one party may not have any expertise in labelling its initial dataset. Experiments show that we can obtain the output, i.e., the accuracy of the updated model, with time many orders of magnitude faster than a protocol using entirely FHE operations.