Privacy-Preserving Federated Recurrent Neural Networks

by   Sinem Sav, et al.

We present RHODE, a novel system that enables privacy-preserving training of and prediction on Recurrent Neural Networks (RNNs) in a federated learning setting by relying on multiparty homomorphic encryption (MHE). RHODE preserves the confidentiality of the training data, the model, and the prediction data; and it mitigates the federated learning attacks that target the gradients under a passive-adversary threat model. We propose a novel packing scheme, multi-dimensional packing, for a better utilization of Single Instruction, Multiple Data (SIMD) operations under encryption. With multi-dimensional packing, RHODE enables the efficient processing, in parallel, of a batch of samples. To avoid the exploding gradients problem, we also provide several clip-by-value approximations for enabling gradient clipping under encryption. We experimentally show that the model performance with RHODE remains similar to non-secure solutions both for homogeneous and heterogeneous data distribution among the data holders. Our experimental evaluation shows that RHODE scales linearly with the number of data holders and the number of timesteps, sub-linearly and sub-quadratically with the number of features and the number of hidden units of RNNs, respectively. To the best of our knowledge, RHODE is the first system that provides the building blocks for the training of RNNs and its variants, under encryption in a federated learning setting.


page 8

page 14


POSEIDON: Privacy-Preserving Federated Neural Network Learning

In this paper, we address the problem of privacy-preserving training and...

HybridAlpha: An Efficient Approach for Privacy-Preserving Federated Learning

Federated learning has emerged as a promising approach for collaborative...

Tile Tensors: A versatile data structure with descriptive shapes for homomorphic encryption

Moving from the theoretical promise of Fully Homomorphic Encryption (FHE...

Privacy-Preserved Blockchain-Federated-Learning for Medical Image Analysis Towards Multiple Parties

To share the patient’s data in the blockchain network can help to learn ...

FPGA-Based Hardware Accelerator of Homomorphic Encryption for Efficient Federated Learning

With the increasing awareness of privacy protection and data fragmentati...

ARIBA: Towards Accurate and Robust Identification of Backdoor Attacks in Federated Learning

The distributed nature and privacy-preserving characteristics of federat...

Hercules: Boosting the Performance of Privacy-preserving Federated Learning

In this paper, we address the problem of privacy-preserving federated ne...

Please sign up or login with your details

Forgot password? Click here to reset