Toward video tampering exposure: inferring compression parameters from pixels.

Johnston, Pamela; Elyan, Eyad; Jayne, Chrisina

Abstract

Video tampering detection remains an open problem in the field of digital media forensics. Some existing methods focus on recompression detection because any changes made to the pixels of a video will require recompression of the complete stream. Recompression can be ascertained whenever there is a mismatch between compression parameters encoded in the syntax elements of the compressed bitstream and those derived from the pixels themselves. However, deriving compression parameters directly and solely from the pixels is not trivial. In this paper we propose a new method to estimate the H.264/AVC quantisation parameter (QP) in frame patches from raw pixels using Convolutional Neural Networks (CNN) and class composition. Extensive experiments show that QP of key-frames can be estimated using CNN. Results also show that accuracy drops for predicted frames. These results open new, interesting research directions in the domain of video tampering/forgery detection.

Citation

JOHNSTON, P., ELYAN, E. and JAYNE, C. 2018. Toward video tampering exposure: inferring compression parameters from pixels. In Pimenidis, E. and Jayne, C. (eds.) Proceedings of the 19th International conference on engineering applications of neural networks (EANN 2018), 3-5 September 2018, Bristol, UK. Communications in computer and information science, 893. Cham: Springer [online], pages 44-57, Available from: https://doi.org/10.1007/978-3-319-98204-5_4

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 19th International conference on engineering applications of neural networks (EANN 2018)
• Start Date: Sep 3, 2018
• End Date: Sep 5, 2018
• Acceptance Date: May 31, 2018
• Online Publication Date: Jul 27, 2018
• Publication Date: Jul 27, 2018
• Deposit Date: Oct 15, 2018
• Publicly Available Date: Jul 28, 2019
• Print ISSN: 1865-0929
• Electronic ISSN: 1865-0937
• Publisher: Springer
• Peer Reviewed: Peer Reviewed
• Pages: 44-57
• Series Title: Communications in computer and information science
• Series Number: 893
• Series ISSN: 1865-0937
• ISBN: 9783319982038
• DOI: https://doi.org/10.1007/978-3-319-98204-5_4
• Keywords: CNN; Compression; Video tampering detection
• Public URL: http://hdl.handle.net/10059/3170
• Contract Date: Oct 15, 2018