Deep forgery detection method and device, storage medium and electronic equipment

Abstract

The invention relates to a deep forgery detection method and device, a storage medium and electronic equipment, and aims to improve the generalization performance of a deep forgery detection model so as to improve the scene applicability of deep forgery detection. The method comprises the following steps: acquiring a to-be-detected target image; inputting the target image into a deep forgery detection model to determine whether the target image is a real face image, wherein a training sample of the deep forgery detection model comprises a real face sample image and a counterfeit face sample image; and a training step of the deep forgery detection model comprising the following steps: generating a first adversarial sample image corresponding to the real face sample image and a second adversarial sample image corresponding to the counterfeit face sample image through a generator, and adjusting parameters of the deep forgery detection model according to the first adversarial sample image and the second adversarial sample image.

Description

technical field [0001] The present disclosure relates to the technical field of image processing, and in particular, to a deep forgery detection method, device, storage medium and electronic equipment. Background technique [0002] With the rapid development of computer vision and graphics, AI (Artificial Intelligence, artificial intelligence)-based deep fake (Deepfake) technology has also been developed rapidly, for example, it has been possible to generate more and more realistic fake face images or videos. The abuse of deepfake data has brought a lot of security risks and privacy risks. Therefore, the detection task (Deepfake Detection) for deep fake data has also received more and more attention. [0003] In related technologies, a deep forgery detection model is usually trained based on specific training data, for example, a deep forgery detection model is trained through forged face images with class labels, so as to realize deep forgery detection. If the forged data...

AI Technical Summary

Problems solved by technology

If the fake data to be detected in the application phase is generated by a different forgery method than the specific training data, the deep fake detection model cannot effectively detect the fake data

That is, deep forgery detection in related technologies faces the problem of being difficult to generalize to identify fake data in different scenarios

Images