Abstract: A method for privacy preservation for machine learning networks includes splitting a trained neural network into a first part and a second part. The first part is a privacy preservation (PP) encoder and the second part is a PP machine learning (ML) model. The method further includes retraining the PP encoder and the PP ML model.

Abstract: Systems and method for training a shared machine learning (ML) model. A method includes generating, by a first entity, a data transformation function; sharing, by the first entity, the data transformation function with one or more second entities; creating a first private dataset, by the first entity, by applying the data transformation function to a first dataset of the first entity; receiving one or more second private datasets, by the first entity, from the one or more second entities, each second private dataset having been created by applying the data transformation function to a second dataset of the second entity; and training a machine learning (ML) model using the first private dataset and the one or more second private datasets to produce a trained ML model.

Abstract: Systems and method for training a shared machine learning (ML) model. A method includes generating, by a first entity, a data transformation function; sharing, by the first entity, the data transformation function with one or more second entities; creating a first private dataset, by the first entity, by applying the data transformation function to a first dataset of the first entity; receiving one or more second private datasets, by the first entity, from the one or more second entities, each second private dataset having been created by applying the data transformation function to a second dataset of the second entity; and training a machine learning (ML) model using the first private dataset and the one or more second private datasets to produce a trained ML model.

Abstract: A method for operating a virtualized radio access point (vRAP) includes: providing a digital signal processor (DSP) pipeline including a number of DSP workers for execution of a plurality of threads of a physical layer (PHY) of the vRAP, wherein a thread of the plurality of threads includes a sequence of processing tasks, including at least one of processing an uplink, UL, subframe, performing UL and downlink, DL, resource scheduling and processing a DL subframe; and interlinking at least three dedicated DSP workers of the DSP pipeline in such a way that different processing tasks of the thread are executed in parallel.

Abstract: Systems and method for training a shared machine learning (ML) model. A method includes generating, by a first entity, a data transformation function; sharing, by the first entity, the data transformation function with one or more second entities; creating a first private dataset, by the first entity, by applying the data transformation function to a first dataset of the first entity; receiving one or more second private datasets, by the first entity, from the one or more second entities, each second private dataset having been created by applying the data transformation function to a second dataset of the second entity; and training a machine learning (ML) model using the first private dataset and the one or more second private datasets to produce a trained ML model.

Abstract: A method of allocating network slices of a network infrastructure includes receiving a network slice request for network resources of the network infrastructure in a form of a network slice. The network slice request includes a service level agreement (SLA) and an associated payoff. It is determined whether to accept the network slice based on whether it is expected that a utility function will be better served by accepting the network slice request or waiting for a further network slice request. It is determined whether the SLA would be fulfilled prior to allocating the network slice. The network slice is allocated and installed in the network infrastructure. Whether the utility function is better served can be determined using a value iteration algorithm or an adaptive algorithm.

Abstract: A method of allocating network slices of a network infrastructure includes receiving a network slice request for network resources of the network infrastructure in a form of a network slice. The network slice request includes a service level agreement (SLA) and an associated payoff. It is determined whether to accept the network slice based on whether it is expected that a utility function will be better served by accepting the network slice request or waiting for a further network slice request. It is determined whether the SLA would be fulfilled prior to allocating the network slice. The network slice is allocated and installed in the network infrastructure. Whether the utility function is better served can be determined using a value iteration algorithm or an adaptive algorithm.