Federal learning-based GitHub sensitive information leakage detection method, apparatus and device, and computer storage medium

The invention discloses a federated learning-based GitHub sensitive information leakage detection method, apparatus and device, and a computer storage medium. The detection method comprises the steps of receiving scanning results of a plurality of electronic devices participating in federated learning on pre-allocated to-be-detected warehouse data; performing convolution hash processing on the scanning result of each electronic device to obtain a scanning result fingerprint; performing sensitive category analysis on the scanning result fingerprints by using the trained classification model to obtain a sensitive category membership degree corresponding to the scanning result of each electronic device; and according to the sensitive category membership degree and a preset threshold value, detecting whether sensitive information leakage exists in the to-be-detected warehouse data scanned by the corresponding electronic equipment, and sending a detection result to the corresponding electronic equipment. According