Motion Vector-Domain Video Steganalysis Exploiting Skipped Macroblocks

TL;DR

This paper introduces a new feature set based on skipped macroblocks for detecting motion vector-based video steganography, improving detection accuracy especially at lower embedding capacities and maintaining robustness under recompression.

Contribution

It proposes an 11-dimensional feature set derived from skipped macroblocks, enhancing detection of MV-based video steganography beyond existing MV-only methods.

Findings

Achieves high detection accuracy at low embedding capacities

Maintains performance robustness under recompression with mismatched QP

Outperforms existing MV-based steganalysis methods

Abstract

Video steganography has the potential to be used to convey illegal information, and video steganalysis is a vital tool to detect the presence of this illicit act. Currently, all the motion vector (MV)-based video steganalysis algorithms extract feature sets directly on the MVs, but ignoring the steganograhic operation may perturb the statistics distribution of other video encoding elements, such as the skipped macroblocks (no direct MVs). This paper proposes a novel 11-dimensional feature set to detect MV-based video steganography based on the above observation. The proposed feature is extracted based on the skipped macroblocks by recompression calibration. Specifically, the feature consists of two components. The first is the probability distribution of motion vector prediction (MVP) difference, and the second is the probability distribution of partition state transfer. Extensive experiments on different conditions demonstrate that the proposed feature set achieves good detection accuracy, especially in lower embedding capacity. In addition, the loss of detection performance caused by recompression calibration using mismatched quantization parameters (QP) is within the acceptable range, so the proposed method can be used in practical scenarios.