System and method for radio frequency fingerprinting

A computer-implemented method comprising:

• monitoring wireless data transmissions representing a beamforming process of a wireless communication protocol between at least one wireless access point (AP) and a plurality of wireless stations (STAs) to obtain a plurality of beamforming dataframes transmitted by said STAs;
• calculating, from said plurality of dataframes, a plurality of feature vectors representing said plurality of dataframes;
• at a training stage, training a machine learning model on a training dataset comprising:
• said plurality of feature vectors, and
• (ii) labels indicating associations between said plurality of feature vectors and said STAs;
• and
• at an inference stage, applying said trained machine learning model to a target wireless data transmission representing estimation of a wireless channel, to predict whether said target wireless data transmission was transmitted from one of said STAs.

A computer-implemented method comprising:

• monitoring wireless data transmissions representing a beamforming process of a wireless communication protocol between multiple pairings selected from among a plurality of wireless access points (APs) and a plurality of wireless stations (STAs) to obtain a plurality of beamforming dataframes transmitted by said STAs;
• calculating, from said plurality of dataframes, a plurality of feature vectors representing said plurality of dataframes;
• at a training stage, training a machine learning model on a training dataset comprising:
• said plurality of feature vectors, and
• (ii) labels indicating a CFO value associated with each of said monitored transmissions;
• and
• at an inference stage, applying said trained machine learning model to a target wireless data transmission representing a beamforming process of a wireless communication protocol between a target STA and AP, to predict a CFO value associated with said target wireless data transmission.