Check patentability & draft patents in minutes with Patsnap Eureka AI!

Covert communication method based on constructive adversarial sample

A technology against samples and covert communication, which is applied in the field of secret data transmission to achieve the effect of improving concealment and high security

Pending Publication Date: 2020-07-14
SHANGHAI UNIV
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

According to the survey, there is no related work on the use of deep neural networks to realize covert communication.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Covert communication method based on constructive adversarial sample
  • Covert communication method based on constructive adversarial sample
  • Covert communication method based on constructive adversarial sample

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] Specific embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0035] First, suppose the sender and receiver want to transmit a secret message b i ∈{0,1}, i=1,2,...,N.

[0036] Such as figure 1 with figure 2 As shown, a covert communication method based on constructive adversarial examples, the specific operation steps are as follows:

[0037] Step 1: The sender and the receiver agree in advance to choose a deep neural network As a secret information extraction tool, and from the model Randomly select a set of images from the public dataset of X as the candidate trigger set X cand .

[0038] Step 2: The sender sends the secret information b i Grouping, with k bits as a group, and from the candidate trigger set X cand Assign a sample image x to each set of secret information.

[0039] Step 3: The sender according to each set of secret information b i ∈{0,1},i=1,2,…,k, where k must not be great...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a covert communication method based on a constructive adversarial sample. The method is a covert communication method for hiding a mapping relationship between an adversarial sample without secret information and the secret information in a public neural network. Different from steganography, the method is advantageous in that the communication content of the sender and thereceiver does not contain secret information. And by utilizing a public image classification network, the sender performs quantitative coding on the labels of part of the sample images according to the secret information to obtain a correct 'soft label 'with low confidence. An adversarial sample is constructed according to the loss value between the soft label and the real label. An adversarial sample does not contain secret information, but can be mapped into a secret-containing 'soft label 'through a specific public model. Therefore, only a constructed type confrontation sample needs to be transmitted between the two communication parties, and the receiver inputs the confrontation sample into the public model and decodes the prediction result to obtain the secret information.

Description

technical field [0001] The invention relates to the field of secret data transmission, in particular to a covert communication method based on constructive confrontation samples. It is a covert communication that uses a public image classification network as a tool for extracting secret information, and the two parties in the communication only need to transmit constructive adversarial samples to realize the transmission of secret information. Background technique [0002] Covert communication is the secure transmission of secret information from a sender to a receiver without arousing the suspicion of a third party. Steganography is an important way to realize covert communication. Steganography embeds secret information by slightly modifying the carrier signal, and the two parties of the communication carry out covert communication by transmitting the secret signal. Therefore, a lot of steganography work is dedicated to reducing the loss of the original signal by embeddi...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): H04K1/00G06N3/04
CPCH04K1/00G06N3/045
Inventor 张新鹏王江锋姚宇巍吴汉舟冯国瑞
Owner SHANGHAI UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com