通过人脸生物特征异常检测深度伪造视频，提升识别准确性。
Detecting Deepfake Talking Heads from Facial Biometric Anomalies
- 利用人脸生物特征中的不自然模式进行检测。
- 在多种深度伪造技术上验证了高准确率。
- 适用于未见过的生成器，适合安全与内容审核场景。
语音克隆与逼真虚拟形象、换脸或唇同步深度伪造视频的结合，使得伪造任何人说任何话变得极为容易。如今，此类深度伪造行为常被用于欺诈、诈骗和政治虚假信息传播。本文提出一种新型的取证机器学习方法，通过分析人脸生物特征中的异常模式来检测深度伪造视频。我们在大规模深度伪造技术与伪装样本数据集上评估该方法，并检验其对视频清洗（laundering）的鲁棒性以及对先前未见生成器的泛化能力。
原文摘要 · Abstract (English)
The combination of highly realistic voice cloning, along with visually compelling avatar, face-swap, or lip-sync deepfake video generation, makes it relatively easy to create a video of anyone saying anything. Today, such deepfake impersonations are often used to power frauds, scams, and political disinformation. We propose a novel forensic machine learning technique for the detection of deepfake video impersonations that leverages unnatural patterns in facial biometrics. We evaluate this technique across a large dataset of deepfake techniques and impersonations, as well as assess its reliability to video laundering and its generalization to previously unseen video deepfake generators.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。