Secure Linear Aggregation Using Decentralized Threshold Additive Homomorphic Encryption For Federated Learning
This addresses privacy and efficiency challenges in federated learning for applications requiring linear computations, but it is incremental as it builds on existing frameworks and encryption schemes.
The paper tackles the problem of secure linear aggregation in federated learning, enabling servers to perform linear computations like multiplication and summation on private user inputs with privacy protection, using decentralized threshold additive homomorphic encryption, and evaluates communication and computation costs showing that elliptic curve-based methods are user-friendly and lattice-based ones are computationally light for servers.
Secure linear aggregation is to linearly aggregate private inputs of different users with privacy protection. The server in a federated learning (FL) environment can fulfill any linear computation on private inputs of users through the secure linear aggregation. At present, based on pseudo-random number generator and one-time padding technique, one can efficiently compute the sum of user inputs in FL, but linear calculations of user inputs are not well supported. Based on decentralized threshold additive homomorphic encryption (DTAHE) schemes, this paper provides a secure linear aggregation protocol, which allows the server to multiply the user inputs by any coefficients and to sum them together, so that the server can build a full connected layer or a convolution layer on top of user inputs. The protocol adopts the framework of Bonawitz et al. to provide fault tolerance for user dropping out, and exploits a blockchain smart contract to encourage the server honest. The paper gives a security model, security proofs and a concrete lattice based DTAHE scheme for the protocol. It evaluates the communication and computation costs of known DTAHE construction methods. The evaluation shows that an elliptic curve based DTAHE is friendly to users and the lattice based version leads to a light computation on the server.