Detection of duplicated data for non-fungible tokens

A computer-implemented method, comprising:

• accessing, by a computer system comprising a processor, a digital artwork image that was created by a user device;
• transmitting, by the computer system, the digital artwork image to a third-party server;
• retrieving, by the computer system, a set of plagiarism probabilities from the third-party server, wherein the third-party server generates the set of plagiarism probabilities by comparing the digital artwork image to a set of cached digital artwork images, wherein a given plagiarism probability in the set of plagiarism probabilities indicates a likelihood that the digital artwork image was derived from a given cached digital artwork image in the set of cached digital artwork images, wherein the comparing comprises, for each cached digital artwork image:
• providing the digital artwork image and the cached digital artwork image to an input layer of a machine learning model;
• wherein the digital artwork image and the cached digital artwork image complete a forward pass through one or more hidden layers of the machine learning model;
• and
• wherein an output layer of the machine learning model produces the plagiarism probability respective of the cached digital artwork image;
• calculating, by the computer system, an authenticity score for the digital artwork image based on the set of plagiarism probabilities;
• and
• determining, by the computer system, that the authenticity score for the digital artwork image satisfies a threshold authenticity value.

A non-transitory computer program product for facilitating detection of data duplication issues relating to generation of non-fungible tokens, the non-transitory computer program product comprising a computer-readable medium having program instructions embodied therewith, the program instructions executable by a processor to cause a computer system comprising the processor to perform operations comprising:

• accessing a digital artwork image;
• accessing a set of cached digital artwork images;
• generating a set of plagiarism probabilities by comparing, via execution of a trained machine learning model, the digital artwork image to the set of cached digital artwork images, wherein a given plagiarism probability in the set of plagiarism probabilities indicates a likelihood that the digital artwork image was derived from a given cached digital artwork image in the set of cached digital artwork images, wherein the comparing comprises, for each cached digital artwork image:
• providing the digital artwork image and the cached digital artwork image to an input layer of a machine learning model;
• wherein the digital artwork image and the cached digital artwork image complete a forward pass through one or more hidden layers of the machine learning model;
• and
• wherein an output layer of the machine learning model produces the plagiarism probability respective of the cached digital artwork image;
• calculating an authenticity score for the digital artwork image based on the set of plagiarism probabilities;
• and
• determining whether the authenticity score satisfies a threshold authenticity value.