Structural steganography method and system based on positions of game beans of bean eaters
By converting secret information into tensors and using the combination of automatic encoder and the bean position in Pac Man game, the problem of traditional steganography being easily detected is solved, and information concealment with high concealment and security is achieved without affecting the normal operation of the game.
CN119728100AInactive Publication Date: 2025-03-28WUXI UNIV
0 Cites 0 Cited by
Patent Information
- Application Number
- CN202411821117.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-11
- Publication Date
- 2025-03-28
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Technical Problem
Traditional steganography is easy to be detected, and the prior art is difficult to find a method between information security and game entertainment that can not only improve steganography capacity and robustness without affecting the normal operation of the game.
Method used
By converting the secret information into a tensor and inputting it into an autoencoder, compressing it into a hidden layer, hiding the information using the bean position in Pac Man game, and decoding the original information through the autoencoder.
Benefits of technology
It improves the concealment and security of steganography, and uses the natural dynamic behavior of Pac Man game to make information hiding more hidden and does not affect the normal operation of the game.
✦ Generated by Eureka AI based on patent content.
Abstract
The invention discloses a constructive steganography method and a constructive steganography system based on bean positions of a bean eater game, and the method comprises the following steps: according to a preset bean eater game grid, selecting a preset number of characters of ASCII (American Standard Code for Information Interchange) to carry out secret information construction, constructing an automatic encoder, inputting randomly generated binary data as original data, and inputting the original data; training the automatic encoder for a preset number of times, updating model parameters, converting the constructed secret information into a binary format, then converting the binary format into a tensor, inputting the secret information converted into the tensor into the trained automatic encoder, compressing the data into a hidden layer, reading an incoming bean-eating person game image, and outputting the incoming bean-eating person game image. And analyzing the appearing position of each event segment bean, converting the appearing position into a tensor, decoding the tensor by using an automatic encoder model to obtain binary data of which the output result is original, and obtaining encrypted information. Compared with the prior art, the information coding processing is added before the information is hidden in the graph, and the steganography concealment and safety are improved.
Need to check novelty before this filing date? Find Prior Art