Non-degraded HEVC video steganography method capable of resisting deep learning network detection

Abstract

The invention discloses a non-degraded HEVC video steganography method capable of resisting deep learning network detection. A secret message embedding step is implemented by the following substeps of: counting the number of prediction blocks of a GOP in a video by using an AMVP technology; constructing a secret embedding index sequence; calculating the distortion cost of carrying out + / -1 modification on prediction indexes of the prediction blocks in sequence according to a decoding sequence; embedding a secret message into the index sequence by utilizing STC coding; comparing index value change conditions before and after secret embedding, and updating a motion vector residual error; and entropy-encoding the modified data again and writing the encoded data back to a video code stream. An extraction step is implemented by the following substeps of: counting the number of prediction blocks of the GOP in the video by using the AMVP technology; constructing and extracting a secret message index sequence; setting an STC code parity check matrix according to an embedding rate, and extracting a secret message; repeatedly extracting until the secret message is completely extracted. The non-degraded HEVC video steganography method has the advantages of unchanged video quality and unchanged motion vector statistical distribution after steganography, and can effectively resist a deep learning network detector taking the reduction of the quality of the secret-embedded video as a detection basis.

Description

technical field [0001] The invention relates to the technical field of information hiding of digitally coded videos, in particular to a non-degraded HEVC video steganography method capable of resisting deep learning network detection. Background technique [0002] As a new-generation video compression standard replacing the H.264 standard, the HEVC standard has better compression performance and is more suitable for the transmission and storage requirements of high-definition and ultra-clear resolution videos, and has been applied on a large scale. Research on steganographic methods for HEVC compressed video is of great significance. The steganography of HEVC video mostly follows the steganography strategy of previous video compression standards (H.264 or MPEG), including spatial domain steganography and compressed domain steganography. Popular steganography in the compressed domain has methods of modifying compression coding parameters such as motion vectors, intra predict...

AI Technical Summary

Problems solved by technology

[0003] On the other hand, Hu Yongjian and others published a paper "Large-capacity lossless HEVC information hiding method for modifying flag bits" in the "Journal of South China University of Technology (Natural Science Edition)" in 2018, and proposed a modified motion vector candidate list index The steganographic method, although this method will not cause the degradation of video quality, but its steganographic encoding is the traditional least significant bit replacement (LSBR) method, the embedding efficiency is low, and due to the sequential embedding, it is non-adaptive to find the best embedding position, resulting in a significant increase in the video bit rate

Images