Image model hidden backdoor detection method and system, storage medium and terminal

Abstract

The invention discloses an image model hidden backdoor detection method and system, a storage medium and a terminal.Compared with the prior art, each training sample image is converted into a frequency spectrum image, target detection is conducted on the frequency spectrum image, and a target image is obtained; the method comprises the following steps: extracting a target image from a frequency spectrum image corresponding to the target image and taking the target image as to-be-determined frequency spectrum image fragments, respectively counting the number of each same to-be-determined frequency spectrum image fragment, and determining a trigger pattern embedded in the frequency spectrum image according to the number of each same to-be-determined frequency spectrum image fragment; and finally, based on the trigger pattern, determining a frequency spectrum image where the trigger pattern is located so as to complete detection of the back door sample image with the trigger pattern, thereby solving the problem that the trigger pattern is hidden on the training sample image and is difficult to detect.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a detection method and system, a storage medium, and a terminal for an image model concealed backdoor. Background technique [0002] With the development of artificial intelligence, machine learning models have been widely used in various industries and play a very important role in various scenarios. Backdoor attack is an emerging attack method against machine learning models. The attacker will bury the backdoor in the model, so that the infected model behaves normally under normal circumstances. But when the backdoor is activated, the output of the model will become the malicious target set by the attacker in advance. [0003] Taking the image model as an example, the attacker adds the identification of a small area to some pictures in the training data set, and specifies the label of the picture as a specific target. The deep neural network trained using the data set...

AI Technical Summary

Problems solved by technology

[0005] In view of this, the present invention provides a method, system, storage medium, and terminal for detecting hidden backdoors of image models, the main purpose of which is to solve the problem that existing trigger patterns are difficult to be detected on training sample images

Images