Video interframe forgery detection: Classification, technique & new dataset

Abstract

Multimedia communication as well as other related innovations are gaining tremendous growth in the modern technological era. Even though digital content has traditionally proved to be a piece of legitimate evidence. But the latest technologies have lessened this trust, as a variety of video editing tools have been developed to modify the original video. Therefore, in order to resolve this problem, a new technique has been proposed for the detection of duplicate video sequences. The present paper utilizes gray values to extract Hu moment features in the current frame. These features are further used for classification of video as authentic or forged. Afterwards there was also need to validate the proposed technique using training and test dataset. But the scarcity of training and test datasets, however, is indeed one of the key problems to validate the effectiveness of video tampering detection techniques. In this perspective, the Video Forensics Library for Frame Duplication (VLFD) dataset has been introduced for frame duplication detection purposes. The proposed dataset is made of 210 native videos, in Ultra-HD and Full-HD resolution, captured with different cameras. Every video is 6 to 15 seconds in length and runs at 30 frames per second. All the recordings have been acquired in three different scenarios (indoor, outdoor, nature) and in landscape mode(s). VLFD includes both authentic and manipulated video files. This dataset has been created as an initial repository for manipulated video and enhanced with new features and new techniques in future.

Scene Change aware Inter-Frame Forgeries Detection Technique for Surveillance Videos Based on Similarities Analysis

“…As mentioned earlier, a video forgery can be insertion, duplication and deletion, or combination of insertion/deletion or duplication, the developed techniques also exhibits same characteristics that is, one aspect which is insertion, duplication or deletion Wang and Farid (2006); Ling & Chang (2012) and Sharma et al,(2021), combination of any two between insertion, duplication and deletion Feng et al,(2011); Bestagini et al, (2011);Wu, Jiang & Wang (2014);Yang et al, (2016) and Bakas et al (2019) and all three aspects of frame forgery (Zhao et al, 2020, Anas et al, 2022. Zhao et al, (2018) proposed a scheme which detects all the three aspect of frame forgeries by exploring the similarity analysis of the frame based on the correlation of statistical anomalies.…”

A New Dataset for Forged Smartphone Videos Detection: Description and Analysis

“…In another work, a similar dataset also named GRIP which is developed by D'Amino et al [19] using copy-move forgery in 15 videos by utilizing the software Adobe After Effects Pro. This video forgery dataset is publicly accessible 5 .…”

“…The results of the analysis can be utilized to assess existing tasks. Some of the other existing video forgery datasets available are [23], [24] , [25], [26], [5]. More detailed summary of the existing video forgery dataset is described in Table 1.…”

“…The dataset's structure is discussed and given in detail in this paper. The use of footage from multiple smartphones is a distinctive feature in this dataset, as other datasets use different single-lens reflex cameras and other closed-circuit television camera, which are difficult to mobilize and expensive to purchase compared to smartphones [5]. Our knowledge of the source of the videos covers a wide range of methods, from Photo Response Non Uniformity (PRNU) methods to Deep Learning methods [6].…”

An Inter-Frame Forgery Detection Technique for Surveillance Videos Based on Analysis of Similarities

“…In literature, techniques were proposed to detect different video tampering methods. Wang &Farid (2006), Ling & Chang (2012) and Sharma et al,(2021) proposed techniques that detects frame duplication. Wang &Farid (2007), Fenget al,(2011 and Bakaset al (2019) proposed frame deletion techniques.…”