A Digital Forensic Technique for Inter–Frame Video Forgery Detection Based on 3D CNN

Bakas, Jamimamul; Naskar, Ruchira

doi:10.1007/978-3-030-05171-6_16

Cited by 25 publications

(12 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This paper used the Siamese network with the ReSnet network to identify duplicated frames. Bakas and Naskar [ 20 ] detected frame insertion, duplication and deletion using a 3D convolutional neural network that used another CNN layer, which was used for temporal information extraction from videos. Li et al [ 21 ] extracted features and localized abnormal points.…”

Section: Related Workmentioning

confidence: 99%

Detecting and Locating Passive Video Forgery Based on Low Computational Complexity Third-Order Tensor Representation

2021

View full text Add to dashboard Cite

Great attention is paid to detecting video forgeries nowadays, especially with the widespread sharing of videos over social media and websites. Many video editing software programs are available and perform well in tampering with video contents or even creating fake videos. Forgery affects video integrity and authenticity and has serious implications. For example, digital videos for security and surveillance purposes are used as evidence in courts. In this paper, a newly developed passive video forgery scheme is introduced and discussed. The developed scheme is based on representing highly correlated video data with a low computational complexity third-order tensor tube-fiber mode. An arbitrary number of core tensors is selected to detect and locate two serious types of forgeries which are: insertion and deletion. These tensor data are orthogonally transformed to achieve more data reductions and to provide good features to trace forgery along the whole video. Experimental results and comparisons show the superiority of the proposed scheme with a precision value of up to 99% in detecting and locating both types of attacks for static as well as dynamic videos, quick-moving foreground items (single or multiple), zooming in and zooming out datasets which are rarely tested by previous works. Moreover, the proposed scheme offers a reduction in time and a linear computational complexity. Based on the used computer’s configurations, an average time of 35 s. is needed to detect and locate 40 forged frames out of 300 frames.

show abstract

Section: Related Workmentioning

confidence: 99%

Detecting and Locating Passive Video Forgery Based on Low Computational Complexity Third-Order Tensor Representation

2021

View full text Add to dashboard Cite

show abstract

“…Penelitian yang dilakukan adalah mengusulkan teknik forensik digital untuk mendeteksi pemalsuan video antar fraeme berdasarkan 3D Convolutional Neural Network (3D-CNN). Hasil dari penelitian ini dengan menerapkan metode 3D CNN mampu mendeteksi penyisipan frame penghapusan frame dan jenis duplikasi pemalsuan pada video [18]. Penelitian ke empat dengan tema sejenis pernah dilakukan dengan judul A Video Forensic Fremework for the unsupervised analysis of MP$-like file Container.…”

Section: Pendahuluanunclassified

Penerapan Metode Localization Tampering dan Hashing untuk Deteksi Rekayasa Video Digital

Alfian

Umar

Fadlil

2021

RESTI

View full text Add to dashboard Cite

The development of digital video technology which is increasingly advanced makes digital video engineering crimes prone to occur. The change in digital video has changed information communication, and it is easy to use in digital crime. One way to solve this digital crime case is to use the NIST (National Institute of Standards and Technology) method for video forensics. The initial stage is carried out by collecting data and carrying out the process of extracting the collected results. A local hash and noise algorithm can then be used to analyze the resulting results, which will detect any digital video interference or manipulation at each video frame, and perform hash analysis to detect the authenticity of the video. In digital video engineering, histogram analysis can be performed by calculating the histogram value metric, which is used to compare the histogram values of the original video and video noise and make graphical comparisons. The results of the difference in frame analysis show that the results of the video show that the 2nd to 7th frames experience an attack while the histogram calculation of the original video centroid value and video tampering results in different values in the third frame, namely with a value of 124.318 and the 7th frame of the video experiencing a difference in the value of 105,966 videos. tampering and 107,456 in the original video. Hash analysis on video tampering results in an invalid SHA-1 hash, this can prove that the video has been manipulated.

show abstract

“…Video compression based features (Yu et al 2016;Aghamaleki and Behrad 2016; are nothing other than video compression footprints, generated during video encoding and decoding process, utilize for forgery detection. Deep learning based methods (Long et al 2017;Bakas and Naskar 2018) extract automated suitable temporal domain features from the training samples of the video stream for the above purpose. However, state-of-the-art inter-frame forgery detection techniques are unable to perform object-based forgery detection in videos, given the fact that such forged video frame contents are manipulated in the spatial as well as temporal domain; whereas, inter-frame forgery only affects the temporal domain video features.…”

Section: Introductionmentioning

confidence: 99%

Object-based forgery detection in surveillance video using capsule network

Bakas

Naskar

Nappi

et al. 2021

J Ambient Intell Human Comput

Self Cite

View full text Add to dashboard Cite

Due to the rapid growth of digital multimedia technology, the importance of multimedia data such as digital images/videos is increasing rapidly in diverse domains. This includes surveillance CCTV footages, which act as primary evidences in many court cases, including highly sensitive contexts. Today, with the wide availability of low-cost image/video manipulating software, digital images/videos have become highly vulnerable to manipulation/modification attacks; one such attack is the class of object-based forgery in surveillance videos. In this paper, we propose a Capsule Network based digital forensic technique for detection of object-based forgery in surveillance videos. In the proposed technique, we use motion residual, computed from every video frame, to extract intra-and inter-frame inherent statistical characteristics of the video sequence, as the input of capsule network. Our experimental results indicate that the proposed technique achieves significant performance in terms of authentic, double compressed and forged frame detection, irrespective of the group of pictures length and degree of compression in videos.

show abstract

A Digital Forensic Technique for Inter–Frame Video Forgery Detection Based on 3D CNN

Cited by 25 publications

References 19 publications

Detecting and Locating Passive Video Forgery Based on Low Computational Complexity Third-Order Tensor Representation

Detecting and Locating Passive Video Forgery Based on Low Computational Complexity Third-Order Tensor Representation

Penerapan Metode Localization Tampering dan Hashing untuk Deteksi Rekayasa Video Digital

Object-based forgery detection in surveillance video using capsule network

Contact Info

Product

Resources

About