Model robustness detection method and device, equipment and medium

Abstract

The embodiment of the invention relates to the technical field of computers, and provides a model robustness detection method and device, equipment and a medium, and the method comprises the steps: obtaining a target image set which comprises at least one adversarial sample image; inputting at least one confrontation sample image to the to-be-attacked target model; obtaining an output result of the target model, wherein the output result comprises the similarity between the original sample image and each adversarial sample image of the input target image set; obtaining robustness detection data of the target model based on the output result and a preset similarity threshold value of the target model; and determining a robustness diagnosis result of the target model according to the robustness detection data. According to the scheme, an objective and accurate robustness diagnosis result can be output for the target model, so that a user can quickly judge the security and reliability of the target model when facing an attack of an adversarial sample.

Description

technical field [0001] The embodiments of the present application relate to the field of computer technology, and in particular to a model robustness detection method, device, equipment and medium. Background technique [0002] With the development of artificial intelligence, Deep Neural Networks (Deep Neural Networks) are widely used in the field of Computer Vision (CV) to enhance Deep Learning (Deep Learning) models. Existing DL models have high security risks and poor reliability in the face of attacks from adversarial samples. [0003] In the field of security, face recognition models are generally used to identify people. This method first collects a large amount of face data to train the model, and then recognizes the faces captured in real time. In the face of the threat of adversarial samples, the main solution is to increase the amount of collected data and expand the training set, thereby improving the accuracy of model recognition. However, such a solution is no...

AI Technical Summary

Problems solved by technology

However, such a solution is not targeted in the face of adversarial attacks, and will still be interfered by the judgment of the model by adversarial samples. Therefore, there is currently a lack of a method for detecting the robustness of the model.

Images