We study the problem of secure transmission over a Gaussian two-user multi-input single-output (MISO) broadcast channel (BC) under the assumption that links connecting the transmitter to the two receivers may have unequal strength statistically. In addition to this, the state of the channel to each receiver is conveyed in a delayed manner to the transmitter. We focus on a two state topological setting of strong v.s. weak links.

We study two-stage biometric identification systems that allow authentication without privacy leakage. In the enrollment phase, secret keys and two layers of the helper data for each user are generated. Additional to the helper data and secret keys, we also introduce private keys in the systems. In the identification phase, an unknown but previously enrolled user is observed, and the user's private key is also presented to the system. The system firstly compares the user with the first layer helper database, outputs a list, and obtains a set of user indices.

How to train a machine learning model while keeping the data private and secure? We present CodedPrivateML, a fast and scalable approach to this critical problem. CodedPrivateML keeps both the data and the model information-theoretically private, while allowing efficient parallelization of training across distributed workers. We characterize CodedPrivateML’s privacy threshold and prove its convergence for logistic (and linear) regression.

We consider the problem of communication over a continuous-time Poisson channel subject to a covertness constraint: The relative entropy between the output distributions when a message is transmitted and when no input is provided must be small. In the absence of both bandwidth and peak-power constraints, we show the covert communication capacity of this channel, in nats per second, to be infinity. When a peak-power constraint is imposed on the input, the covert communication capacity becomes zero, and the “square-root scaling law” applies.

In a private information retrieval (PIR) system, the user needs to retrieve one of the possible messages from a set of storage servers, but wishes to keep the identity of the requested message private from any given server. Existing efforts in this area have made it clear that the efficiency of the retrieval will be impacted significantly by the amount of the storage space allowed at the servers. In this work, we consider the tradeoff between the storage cost and the retrieval cost.