Adversarial sample generation method and device and storage medium

The invention provides an adversarial sample generation method and device and a storage medium, particularly relates to the technical field of target detection, and is used for generating an adversarial sample independent of a target model or a target detector so as to simply and efficiently improve the mobility of the adversarial sample. The adversarial sample generation method comprises the steps of performing semantic segmentation processing on an original image to obtain a feature value of each pixel point in the processed image, the size of the processed image being the same as that of the original image; based on the characteristic value of each pixel point in the processed image, determining region position information of a target object, the target object being an object to be identified in the processed image; and based on the regional position information of the target object, adding disturbance information in the original image to generate a target confrontation sample. 本申请提供一种对抗样本生成方法、装置及存储介质，尤其涉及