PINE: Efficient Norm-Bound Verification for Secret-Shared Vectors Apple Machine Learning Research
Secure aggregation of high-dimensional vectors is a fundamental primitive in federated statistics and learning. A two-server system such as PRIO allows for scalable aggregation of secret-shared vectors. Adversarial clients might try to manipulate the aggregate, so it is important to ensure that each (secret-shared) contribution… Read More »PINE: Efficient Norm-Bound Verification for Secret-Shared Vectors Apple Machine Learning Research