Carrier-free covert communication method and system based on depth discriminator

Abstract

The invention discloses a carrier-free covert communication method and system based on a depth discriminator, and the method comprises the steps: building a code table, collecting a plurality of images, distributing code words with the length of p to each image according to the code table, and building a carrier library; constructing a mapping model by learning a mapping relationship between each image and a corresponding code word, and sending the mapping model to a receiver; converting the secret message into a binary code, and dividing the binary code into a plurality of bit segments according to a set length P; and querying an image corresponding to each bit segment in a carrier library, and sending the formed secret-carrying image sequence to a receiver, so that the receiver recovers the secret message according to the secret-carrying image sequence and the neural network model. By constructing the code table, the depth model capable of automatic learning is trained to realize image-based covert communication, automatic model construction is realized, and the problem that a large amount of image data is difficult to search is solved.

Description

technical field [0001] The invention belongs to the field of information hiding, in particular to a carrierless covert communication method and system based on a depth discriminator. Background technique [0002] With the rapid development of the Internet and digital multimedia processing technology, multimedia content such as images, audio and video has become an important medium for people to communicate. But at the same time, it becomes easier to attack and intercept the transmitted information. Once the important information of the user is intercepted or destroyed, it will bring immeasurable losses. Traditional cryptography algorithms can encrypt important information to ensure the safe transmission of information in the network. However, encrypted information often exists in the form of garbled characters. In some cases, this form is more likely to attract the suspicion and attention of attackers. [0003] In order to achieve a higher level of security communication, ...

AI Technical Summary

Problems solved by technology

Although this method has improved in robustness, it still cannot avoid the problem of a large number of uninspired and no-result-guaranteed searches in order to construct a complete image set

[0008] Chinese patent application CN111416683A discloses a covert communication method based on constructed adversarial examples, which hides the mapping relationship between adversarial examples without secret information and secret information in a public neural network to achieve the purpose of covert communication, but the application needs to construct Specialized Adversarial Example Images

[0010] 1. The transmission capacity of each image is too small, and the image search method can only transmit a dozen bits of information in each image, resulting in a low capacity of this type of method

[0011] 2. Due to the low coverage rate of traditional methods, it is necessary to search large-scale images before carrying out covert communication. In practice, it is often necessary to search hundreds of thousands or even millions of images to have a chance to build a complete vector library

[0012] 3. Poor robustness, when the image is attacked by noise in the network, it will cause the receiver to decode and get wrong information

[0013] 4. There is uncertainty, even if you search a large number of images, you may not find a complete set, and the search process has no rules to follow

Images