• Journal of Digital Forensics
• /
• v.13 no.4
• /
• pp.257-270
• /
• 2019

Recently, due to the popularization of smart devices such as smartphones and the like, photography and video recording audio recordings are frequently and efficiently performed. Thus the use of digital files of those types is increasing. For these digital files to be legally valid as digital evidence, the proof of origin for digital evidence was essential. Mainly, due to the characteristics of the digital audio file, it is possible to make a sophisticated forgery and falsification through the mass copying and digital editing program from the original record. In this way, it has been increasing more and more cases of manipulating digital audio files. In this paper, we propose the procedure of analyzing the file format of digital audio files and the audio signal after the analysis of various actual cases. As a result, it has confirmed that the digital audio files can be not original through traces generated during the manipulation of the digital audio file in case of the manipulated data. Moreover, it has confirmed that the proposed authentication analysis procedure may not clarify whether or not the digital audio file has been a forgery in some specific condition.

• Annual Conference of KIPS
• /
• 2002.11a
• /
• pp.19-22
• /
• 2002

워터마킹(watermarking) 기술은 판매하거나 배포할 자료들 중, 특히 이미지, 오디오, 텍스트, 비디오 및 멀티미디어 데이터 등에 원래의 소유주를 표시할 수 있는 특정 데이터, 즉 워터마크를 넣어 소유주를 확인할 수 있게 하는 저작권 보호(copyright protection)기법으로 근래에 들어 그 필요성이 크게 대두되고 있는 기술이다. 본 논문에서는 wave format 파일을 읽어들여 음향에 효과를 주는 응용프로그램의 불법사용을 막는 데에 대한 저작권 보호를 연구 기술하였다. 원본 없이 추출 가능한 디지털 워터마킹 기법[1]을 음악파일에 삽입하고 응용프로그램이 그것을 추출하여 편집저장할 여부를 결정하도록 하는 방법에 주요 관점을 두고 실험 및 구현을 하였다.

• Journal of Broadcast Engineering
• /
• v.25 no.4
• /
• pp.620-628
• /
• 2020

Automatically predicting video highlight is an important task for media industry and streaming platform providers to save time and cost of manual video editing process. We propose a new ensemble model that combines multiple highlight detectors with each focusing on different parts of highlight events. Therefore, our model can capture more information-rich sections of events. Furthermore, the proposed model can extract improved features for highlight detection particularly when the train video set is small. We evaluate our model on e-sports and baseball videos.

• Journal of KIISE
• /
• v.45 no.3
• /
• pp.311-320
• /
• 2018

Recently, the use of digital audio and video as proof in criminal and all kinds of litigation is increasing, and scientific investigation using digital forensic technique is developing. With the development of computing and file editing technologies, anyone can simply manipulate video files, and the number of cases of manipulating digital data is increasing. As a result, the integrity of the evidence and the reliability of the evidence Is required. In this paper, we propose a technique for extracting the Electrical Network Frequency (ENF) through a grid of power grids according to the geographical environment for power supply, and then performing signal processing for peak detection using QIFFT. Through the detection algorithm using the standard deviation, it was confirmed that the video file was falsified with 73% accuracy and the forgery point was found.