Exposing fake bitrate video and its original bitrate

Abstract

Video bitrate, as one of the important factors that reflect the video quality, can be easily manipulated via some video editing softwares. In some forensic scenarios, for example, video uploaders of video-sharing websites may increase video bitrate for seeking more commercial profits. In this paper, we try to detect those fake high bitrate videos, and then further to estimate their original bitrates. The proposed method is mainly based on the fact that if the video bitrate has been increased with the help of video editing software, its essential video quality will not increase at all. By analyzing the quality of the questionable video and a series of its re-encoded versions with different lower bitrates, we can obtain a feature curve to measure the change of the video quality, and then we propose a compact feature vector (3-D) to expose fake bitrate videos and their original bitrates. The experimental results evaluated on both CIF and QCIF raw sequences have shown the effectiveness of the proposed method.

Video content authentication techniques: a comprehensive survey

“…Although this algorithm was not designed to detect forgeries, it could still serve as a utilitarian preprocessing step that could provide useful hints regarding content authenticity. This algorithm was an extension and improvement of the previous algorithms proposed by the same authors in [119,120]. While the technique in [119] was evaluated on MPEG-2 encoded videos only, in [120], the authors worked on detecting up-converted videos only, without actually determining the original bitrates of these up-converted videos.…”

“…2.1.1.2 detected frame manipulation by looking for evidence of double compression. However, if a forger alters the encoded video directly and creates no second-quantization spatial and/or temporal artifacts, the research in [42,46,50,113,119] would be rendered ineffectual. Furthermore, the anti-forensic approach proposed in [111] seems to have the potential to be molded into a potent digital video antiforensic tool.…”

Exposing Fake Bit Rate Videos and Estimating Original Bit Rates

“…Chen and Shi [12] proposed a method based on Benford's law to detect whether an MPEG-2 video is recompressed from a lower/higher bit rate one, and then Sun et al [13] proposed an improved method based on [12]. In our previous work [22], we proposed a method to expose those fake high bit rate videos up-converted from lower bit rates, and first try to estimate their original bit rates.…”

“…However, our previous work [22] is only evaluated on MPEG-2 compressed videos, thus its effectiveness for other compression schemes such as H.264/AVC needs further evaluation. Besides, the detection accuracy is still far from satisfactory for detecting fake bit rate videos that are up-converted from original higher bit rates.…”

“…Besides, the detection accuracy is still far from satisfactory for detecting fake bit rate videos that are up-converted from original higher bit rates. As the extension of our previous work, this paper would further investigate the specific artifacts of those fake bit rate videos in both frequency and spatial domains, and expand our original 3-D features [22] to 16-D in order to improve the detection performance. Furthermore, more test video clips with four different resolutions (including QCIF, CIF, VGA, and HD720p) and two popular compression schemes (including MPEG-2 and H.264/AVC) are evaluated to make the experimental results more convincing.…”