Fast and Blind Detection of Rate-Distortion-Preserving Video Watermarks

Mareen, Hannes, Van Walledael, Glenn, Lambert, Peter and Khelifi, Fouad (2022) Fast and Blind Detection of Rate-Distortion-Preserving Video Watermarks. In: Proceedings of 15th International Workshop on Digital Forensics (WSDF) 2022. ACM, New York, NY, United States. (In Press)

Preview

Text Fast and Blind Detection of Rate-Distortion-Preserving Video Watermarks Latest.pdf - Accepted Version Download (1MB) | Preview

Abstract

Forensic watermarking enables the tracing of digital pirates that leak copyright-protected multimedia. To prevent a negative impact on the video quality or bit rate, rate-distortion-preserving watermarking exists, which represents a watermark as compression artifacts. However, this method has two main disadvantages; the detection has a high complexity and it is non-blind. Although a method based on perceptual hashing exists that speeds up the detection of a fallback watermarking system, it decreases its robustness. Therefore, this paper proposes a novel fast detection method that has less impact on the robustness than related work. Our method optimized NS-DCT-DST hashes for rate-distortion-preserving watermarking, which are more robust to content-preserving attacks. Moreover, a blind version is proposed which does not require the original video for hash extraction. As such, the detection is up to 5700 times faster, at the cost of a modest decrease in robustness. In fact, the proposed method shows good robustness to content preserving recompression attacks when using hashes that are as small as 432 bytes. This is much smaller than comparable performance of related work. In conclusion, this paper enables fast adversary tracing using watermarks that do not impact the video’s compression efficiency.

Actions (login required)

View Item

Downloads