Detection of re-compression, transcoding and frame-deletion for digital video authentication

Abstract

In the wake of widespread surfeit of inexpensive and user-friendly digital multimedia alteration software, digital images and videos have lost the unparalleled position they once occupied as 'authoritative testament of occurrence of events'. The inherent susceptibility of digital content to malevolent manipulations renders it vulnerable to our skepticism. Establishment of authenticity of digital content is of utmost importance in situations where reliability on fraudulent evidence could have serious consequences.With the intent of tackling a few of the several challenges of the video forensics domain, in this paper we propose a potent DCT coefficient analysis-based forensic technique for reliable detection of re-compression and transcoding in digital videos. This scheme facilitates visually perceptible differentiation between singly-compressed and re-compressed video frames while circumventing the need for undertaking any complicated peak periodicity analysis procedures that are normally associated with traditional DCT-based studies. We also present a unique optical-flow analysis scheme, where, instead of inspecting inconsistencies caused by frame-removal in the entire optical flow sequences of a given video, we focus entirely on the brightness gradient component of this flow. The experiments in this regard substantiate the forensic capabilities of this component and proffer observations conducive to the detection and localization of frame-removal in digital videos. Subjective and quantitative experimentation on a comprehensive dataset under a wide range of experimental set-ups validate the efficacy and resilience of the proposed techniques.

Video content authentication techniques: a comprehensive survey

“…In [72], a hybrid forensic system for the detection of frame-insertion, removal and replication was developed. For the detection of frame-insertion and removal, the system detected irregularities introduced in the brightness gradient component of optical flow by post-production frame-tampering.…”

“…We analyzed the performances of the following interframe forgery detection techniques: the pixel-correlation based approach proposed in [75], the noise-based method of [38], and the optical-flow-based schemes presented in [62,72,632,72]. Table 3 [63,72] detect all three kinds of inter-frame forgeries.…”

“…Table 3 [63,72] detect all three kinds of inter-frame forgeries. The results in Table 3 pertain to the outcomes of the experiments performed with respect to the specific kinds of forgeries each of these techniques detect.…”

“…Desirable detection accuracy was reported in [97], where the proposed algorithm was tested on videos captured by static surveillance cameras. The only techniques in the literature that generated satisfactory results for realistic tampered videos taken from a standard data set SULFA [8] were [72,86,88].…”

Video Inter-frame Forgery Detection Approach for Surveillance and Mobile Recorded Videos

“…Likewise, the authors in [23] and [12] utilized Enhanced Fluctuation Feature (EFF) and Sequence of Average Residual of P-frames (SARP) respectively for frame removal detection with sound accuracy. One of the frame removal detection technique proposed in [24] utilized the measure of brightness variance. Another type of frame based tampering named frame replication was detected by analyzing disturbance in the temporal correlation of all adjacent frame pairs [11].…”