arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.08517cs.CVcs.LGeess.IV
收藏

检测Deepfake视频:三种技术的分析

Detecting Deepfake Videos: An Analysis of Three Techniques

Armaan Pishori, Brittany Rollins, Nicolas van Houten, Nisha Chatwani, Omar Uraimov

摘要:

Deepfake生成算法的最新进展产生了操纵媒体,对隐私,安全和大众传播产生了危险的影响。解决这个问题的努力已经以竞赛和资助研究的形式出现,以检测deepfake。本文介绍了三种技术和算法:卷积LSTM,眨眼检测和灰度直方图-在参与Deepfake检测挑战赛时追求。我们评估了目前关于deepfake视频的知识,这是一种更严重的操纵媒体版本,以及以前使用的方法,并发现灰度直方图技术与其他技术相关。我们讨论了每种方法的影响,并提供了进一步的步骤,以改善给定的结果。

英文摘要:

Recent advances in deepfake generating algorithms that produce manipulated media have had dangerous implications in privacy, security and mass communication. Efforts to combat this issue have risen in the form of competitions and funding for research to detect deepfakes. This paper presents three techniques and algorithms: convolutional LSTM, eye blink detection and grayscale histograms-pursued while participating in the Deepfake Detection Challenge. We assessed the current knowledge about deepfake videos, a more severe version of manipulated media, and previous methods used, and found relevance in the grayscale histogram technique over others. We discussed the implications of each method developed and provided further steps to improve the given findings.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑