Compression noise based video forgery detection

Abstract

Intelligent video editing techniques can be used to tamper videos such as surveillance camera videos, defeating their potential to be used as evidence in a court of law. In this paper, we propose a technique to detect forgery in MPEG videos by analyzing the frame's compression noise characteristics. The compression noise is extracted from spatial domain by using a modified Huber Markov Random Field (HMRF) as a prior for image. The transition probability matrices of the extracted noise are used as features to classify a given video as single compressed or double compressed. The experiment is conducted on different YUV sequences with different scale factors. The efficiency of our classification is observed to be higher relative to the state of the art detection algorithms.

Video forgery detection and localization based on 3D patchmatch

“…In [5] the photon shot noise, which depends on the camera model and recording parameters, is used as an alternative to camera fingerprint for static scenes. Coding-based methods have been considered in [6,7] where artifacts introduced by doublycompressed MPEG videos are used as evidence of tampering.…”

Digital video tampering detection: An overview of passive techniques

“…Fails when G1=G2; As G1 increases, accuracy drops; where G1 and G2 are the GOP sizes of the first and second compression respectively Markov statistics of quantized DCT coefficients Fails if second quantization scale (qs) is same as first; performance degrades when the second compression qs is an odd multiple of first Markov statistics of compression noise (Ravi et al, 2014) Fails if second qs is same as first Pixel estimation in GOP, error between the true and estimated value (Subramanyam and Emmanuel, 2013) Works with fixed GOP; accuracy decreases when the ratio between the first and the second qs is less than 1.3; works with videos from static cameras only Blocking artifact (Luo et al, 2008) Fails when number of frames deleted is an integral multiple of GOP size; works with fixed GOP structure Correlation of a video with its re-encoded version with the same codec and coding parameters Performance degrades if coarse quantization is adopted in the second encoding step; content dependent Number of different coefficients between I-frames of singly and doubly compressed videos, number of different coefficients between I-frames of the corresponding doubly and triply compressed videos Able to address double compression with same bitrate only; performance depends on proper selection of recompression bitrate M A N U S C R I P T…”

“…Each GOP is treated as a detection unit, which will be classified as singly or doubly compressed by Fisher's linear discriminant (FLD) analysis. In (Ravi et al, 2014), compression noise is estimated from the video based on Huber Markov Random Field (HMRF) and maximum a posteriori (MAP) criteria, modeled as first order Markov Process. TPM of size 3 × 3 is calculated in each of the eight directions considering 8-connected neighborhood in 16 × 16 block.…”

Three-dimensional Region Forgery Detection and Localization in Videos

“…If there is an error between the actual value and the calculated value, the video may be compressed several times. In [14], Markov statistics of compression, noise is used to detect double compression, and in [15], with assuming that the second compression has same parameters with the first time of compression at which most of the methods fail, and the basic idea is, when a frame is recompressed with the same quantization matrix again. The number of different DCT coefficients between the sequential two versions will monotonically decrease.…”