Abstract: A method and device for data conversion in a matrix compute apparatus. The apparatus includes an input buffer (IB) that receives one or more matrix inputs characterized by a first format and a compute device coupled to the IB device that is configured to determine a combined matrix output. The compute device determines a first matrix output using a first input portion of the matrix input and determines a second matrix output using a second input portion. The compute device then determines a combined matrix output in a second format using the first and second matrix outputs. Within the compute device, an alignment device can determine a rounded matrix output from the combined matrix output, and a partial products reduction (PPR) device can determine a reduced matrix output in a third format using the rounded matrix output, which is stored in an output buffer (OB) coupled to the compute device.

Abstract: An apparatus to facilitate video motion smoothing is disclosed. The apparatus comprises one or more processors including a graphics processor, the one or more processors including circuitry configured to receive a video stream, decode the video stream to generate a motion vector map and a plurality of video image frames, analyze the motion vector map to detect a plurality of candidate frames, wherein the plurality of candidate frames comprise a period of discontinuous motion in the plurality of video image frames and the plurality of candidate frames are determined based on a classification generated via a convolutional neural network (CNN), generate, via a generative adversarial network (GAN), one or more synthetic frames based on the plurality of candidate frames, insert the one or more synthetic frames between the plurality of candidate frames to generate up-sampled video frames and transmit the up-sampled video frames for display.

Abstract: An apparatus to facilitate deepfake detection models utilizing subject-specific libraries is disclosed. The apparatus includes one or more processors to store a plurality of deepfake detection models corresponding to a plurality of subjects of interest; receive a query to identify whether data pertaining to a target subject of interest is a deepfake, the target subject of interest comprised in the plurality of subjects of interest and associated with a subject identifier (ID); identify a deepfake detection model corresponding to the subject ID; extract features for deepfake detection from the data; input the extracted features to the identified deepfake detection model corresponding to the subject ID; and responsive to an output of the deepfake detection model exceeding a determined deepfake threshold, generate a notification, in response to the query, indicating a possible deepfake attack corresponding to the target subject of interest.

Abstract: A secure electronic marketplace platform is proposed that comprises a server computer equipped with a set of databases, storage systems, payment processing gateway, data analytics engine and a set of user clients to facilitate the sale and purchase of copyrighted digital media entities created by original content creators. Server computer receives a group of one or more copyrighted digital media entities (e.g. digital images) from one group of users and after performing a set of quality assurance related validations, makes them available for purchasing to a second group of users via disclosed platform. By default, limited previews of digital media entities are available via disclosed platform. In addition, users can also purchase a group of one or more digital media entities by registering into the electronic marketplace platform which also requires payment method information.

Abstract: An apparatus to facilitate an authenticator-integrated generative adversarial network (GAN) for secure deepfake generation is disclosed.

Abstract: An apparatus to facilitate generator exploitation for deepfake detection is disclosed. The apparatus includes one or more processors to: alter a generative neural network of a deepfake generator with one or more modifications for deepfake detection; train the generative neural network having the one or more modifications and a discriminative neural network of the deepfake generator, wherein training the generative neural network and the discriminative neural network to facilitate the generative neural network to generate deepfake content comprising the one or more modifications; and communicate identification of the one or more modifications to a deepfake detector to cause the deepfake detector to identify deepfake content generated by the deepfake generator that comprises at least one of the one or more modifications.

Abstract: A method and a system for communication are presented. In one example embodiment, the method includes the step of receiving a first frame of a communication signal. The first frame includes a first plurality of constituents. One or more constituents of the first plurality of constituents of the first frame form a symbol of the first frame. The method includes the step obtaining a second frame. The second frame includes the first plurality of constituents. One or more constituents of the first plurality of constituents of the second frame form a symbol of the second frame. The symbols of the second frame are obtained by creating redundancies of the constituents of the first plurality of one or more symbols of the first frame. The first frame includes a second plurality of constituents. One or more constituents of the second plurality of the first frame form a preamble field of the first frame.

Abstract: A technique for an equal phase combining for a robust orthogonal frequency division multiplexing (OFDM) system under high delay spread channel is disclosed. In one embodiment, a method includes receiving and synchronizing transmitted OFDM symbols having cyclic prefixes via a symbol synchronizer module, removing the cyclic prefixes from the OFDM symbols, via a cyclic prefix remover module, to form time domain symbols, converting the time domain symbols to frequency domain symbols via an FFT module, equalizing a received sub-carrier with complex conjugate of estimated channel coefficients in frequency domain at the same sub-carrier frequency via an equalizer, combining the frequency domain symbols spread over multiple sub-carriers during transmission via a combiner, and detecting phase information from the mapped combined PSK constellation symbol via a detector module.

Abstract: A method and device for adapting a signal is provided. The signal includes a number of recurring samples of data. In one example embodiment, the method receives recurring samples of data. Each of the samples of data includes a first number of elements. A second number of elements are selected from at least one of the recurring samples. The second number of elements is approximately less than the first number of elements. The selected second number of elements are substituted with respective phase altered elements. The subject matter also provides a method and device for identifying a signal property(ies) and a computer system for implementing these methods.

Abstract: A technique for an equal phase combining for a robust orthogonal frequency division multiplexing (OFDM) system under high delay spread channel is disclosed. In one embodiment, a method includes receiving and synchronizing transmitted OFDM symbols having cyclic prefixes via a symbol synchronizer module, removing the cyclic prefixes from the OFDM symbols, via a cyclic prefix remover module, to form time domain symbols, converting the time domain symbols to frequency domain symbols via an FFT module, equalizing a received sub-carrier with complex conjugate of estimated channel coefficients in frequency domain at the same sub-carrier frequency via an equalizer, combining the frequency domain symbols spread over multiple sub-carriers during transmission via a combiner, and detecting phase information from the mapped combined PSK constellation symbol via a detector module.

Abstract: A method and a system for communication are presented. In one example embodiment, the method includes the step of receiving a first frame of a communication signal. The first frame includes a first plurality of constituents. One or more constituents of the first plurality of constituents of the first frame form a symbol of the first frame. The method includes the step obtaining a second frame. The second frame includes the first plurality of constituents. One or more constituents of the first plurality of constituents of the second frame form a symbol of the second frame. The symbols of the second frame are obtained by creating redundancies of the constituents of the first plurality of one or more symbols of the first frame. The first frame includes a second plurality of constituents. One or more constituents of the second plurality of the first frame form a preamble field of the first frame.

Abstract: A method and device for adapting a signal is provided. The signal includes a number of recurring samples of data. In one example embodiment, the method receives recurring samples of data. Each of the samples of data includes a first number of elements. A second number of elements are selected from at least one of the recurring samples. The second number of elements is approximately less than the first number of elements. The selected second number of elements are substituted with respective phase altered elements. The subject matter also provides a method and device for identifying a signal property(ies) and a computer system for implementing these methods.