obsidian6s/feature-extractors-for-video-steganalysis

To provide the stego community with C/C++ implementations of selected feature extractors mainly targeted at H.264 steganography.

Feature Extractors for Video Steganalysis

Name	Dimension	Domain	Proposed	Notes
AoSO	18	Motion Vector	[1]
NPELO	36	Motion Vector	[2]
IDFB	768	Transform Coefficient	[3]
SUPERB	609	Transform Coefficient	[4]

References

[1] K. Wang, H. Zhao, and H. Wang, "Video steganalysis against motion vector-based steganography by adding or subtracting one motion vector value," IEEE Transactions on Information Forensics and Security, vol. 9, no. 5, pp. 741–751, 2014.

[2] H. Zhang, Y. Cao, and X. Zhao, "A Steganalytic Approach to Detect Motion Vector Modification Using Near-Perfect Estimation for Local Optimality," IEEE Transactions on Information Forensics and Security, vol. 12, no. 2, pp. 465–478, 2017.

[3] H. Zhang, W. You, and X. Zhao, "A Video Steganalytic Approach Against Quantized Transform Coefficient-Based H.264 Steganography by Exploiting In-Loop Deblocking Filtering," IEEE Access, vol. 8, pp. 186862–186878, 2020.

[4] Y. Cao, H. Zhang, X. Zhao, and X. He, “Steganalysis of H.264/AVC Videos Exploiting Subtractive Prediction Error Blocks,” IEEE Transactions on Information Forensics and Security, vol. 16, pp. 3326–3338, 2021.