Abstract: There is provided a computer implemented method of explainability of a media element identified as deepfake, comprising: feeding the media element into a deepfake model trained to classify the media element as deepfake or not deepfake, wherein the deepfake model is implemented as a non-explainable model, in response to the deepfake model classifying the media element as deepfake: automatically dividing the media element into a plurality of sub-regions, for each respective sub-region of the plurality of sub-regions, creating a synthetic media element including the respective sub-region and excluding other sub-regions, feeding each of a plurality of synthetic media elements into the deepfake model, in response to the deepfake model classifying at least one of the synthetic media elements as being deepfake, creating a presentation indicating the sub-region corresponding to each at least one synthetic media elements classified as deepfake.

Abstract: There is provided a computer implemented method of training a detection machine learning model (ML) for identifying a specific deepfake tool of a plurality of deepfake tools used to create a deepfake video, comprising: feeding a plurality of sample authentic videos into the specific deepfake tool, obtaining a plurality of deepfake videos as an outcome of the specific deepfake tool, creating a training dataset comprising a plurality of records, wherein a record includes a deepfake video labelled with a ground truth indicating the specific deepfake tool used to create the deepfake video, and training the detection ML model on the training dataset for detecting that the specific deepfake tool was used to create an input deepfake video.

Abstract: There is provided a computer implemented method of detecting a deepfake video, comprising: feeding a video into at least one forensic model, obtaining at least one indication of at least one property of a person or object depicted in the video as an outcome of the at least one forensic model, comparing the at least one indication to at least one ground truth obtained by applying the at least one forensic model to at least one authentic video depicting the person or object and/or by searching a ground truth dataset, in response to a mismatch between the at least one indication and the at least one ground truth, increasing likelihood that the video is deepfake, and in response to a match between the at least one indication and the at least one ground truth, increasing likelihood that the video is authentic.

Abstract: There is provided a computer implemented method of training a detection machine learning model (ML) for identifying a specific deepfake tool of a plurality of deepfake tools used to create a deepfake video, comprising: feeding a plurality of sample authentic videos into the specific deepfake tool, obtaining a plurality of deepfake videos as an outcome of the specific deepfake tool, creating a training dataset comprising a plurality of records, wherein a record includes a deepfake video labelled with a ground truth indicating the specific deepfake tool used to create the deepfake video, and training the detection ML model on the training dataset for detecting that the specific deepfake tool was used to create an input deepfake video.

Abstract: There is provided a computer implemented method of detecting a deepfake video, comprising: analyzing a video, annotating the video according to the analysis, selecting a plurality of verification models according to the annotations, wherein the plurality of verification models include at least one forensic model that is not trained to detect that the video comprises a deepfake video, wherein outcome of the at least one forensic model applied to the video is compared to a ground truth obtained by applying the at least one forensic model to at least one other authentic video having at least one annotation of the video, aggregating a plurality of outcomes of the plurality of verification models, and determining a probability that the video was created by a deepfake tool according to the aggregation.

Abstract: There is provided a computer implemented method of training a customized detector ML model for use on an input video, comprising: analyzing the input video to identify a plurality of features associated with the input video, obtaining a plurality of authentic videos associated with the plurality of features, feeding the plurality of authentic videos into at least one deepfake tool, obtaining a plurality of deepfake videos as an outcome of the at least one deepfake tool, creating a training dataset comprising a plurality of records, wherein at least one first record includes a deepfake video labelled with a ground truth indicating deepfake, and at least one second record includes an authentic video labelled with a ground truth indicating authentic, and training the customized detector ML model on the training dataset.