Video steganalysis method based on motion vector rate-distortion performance estimation

Abstract

The invention relates to a video steganalysis method based on motion vector rate-distortion performance estimation: first, dividing a compression video to be tested into a plurality of frame sets, wherein each frame is composed of continuous video frames, and any video frame only belongs to one frame set; performing steganalysis feature extraction on a frame set including a plurality of motion vectors: for each motion vector in the frame set, obtaining a set composed of the motion vector and an adjacent motion vector, calculating the rate-distortion performance of each motion vector in the set, and extracting preset steganalysis features from the frame set; repeating the steps, and successively performing steganalysis feature extraction on all frame sets of the video to be tested; and employing a classifier based on steganalysis features to perform steganalysis determination on each frame set in the video to be tested. The video steganalysis method can effectively detect a present motion vector domain video steganalysis method.

Description

technical field [0001] The present invention relates to a video steganalysis method, in particular to a video steganalysis method based on motion vector rate-distortion (Rate-Distortion) performance estimation and its application in digital media security protection. It belongs to the subfield of information hiding in the field of information security technology. Background technique [0002] Modern information hiding technology mainly includes Steganography, Steganalysis and Digital Watermarking. Steganography mainly studies how to embed secret information into digital multimedia files such as digital images, videos, and audios to achieve the purpose of covert communication; steganalysis mainly uses methods such as machine learning and pattern recognition to classify and judge the files under test. [0003] With the widespread popularity of video on demand, Internet streaming media and hand-held portable camera equipment, digital video has become the most influential commu...

AI Technical Summary

Problems solved by technology

However, since these methods inevitably destroy the local optimum of the motion vector during the steganographic embedding process, they cannot resist the attack of AoSO, the most effective steganalysis method in the current motion vector domain (references: K.Wang, H. Zhao, and H. Wang, “Video steganalysis against motion vector-based steganography by adding or subtracting one motion vector value,” IEEE Trans. Inf. Forensics Security, vol.9, no.5, pp.741–751, May 2014 .)

Images