Hidden ciphertext algorithm identification method based on deep learning ResNet algorithm

• Main Authors: LI ZHENG, DUANMU KEKE, SUN HANLIN, DANG ZHIHAO, BAI HANGYU, YUAN KE, JIA CHUNFU
• Format: Patent
• Language: Chinese; English
• Published: 23.06.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The invention provides a hidden ciphertext algorithm identification method based on a deep learning ResNet algorithm. The method comprises the steps that an image set is collected, each image in the image set carries a type label, and the type label is used for indicating whether the image is a secret-carrying image or not and indicating a cryptographic algorithm type to which a ciphertext in the secret-carrying image belongs; taking the image set as training data, and training by using a deep learning ResNet algorithm to obtain a classification model 1 used for distinguishing whether the input image is a secret-carrying image; taking all the secret-carrying images as training data, and training by using a deep learning ResNet algorithm to obtain a classification model 2 used for identifying a cryptographic algorithm type to which the ciphertext in the secret-carrying images belongs; inputting a to-be-recognized image into the trained classification model 1, and if a classification result shows that the to-be