📄 中文摘要
随着深伪技术的快速发展，恶意的人脸操控对个人隐私和社会安全构成了重大威胁。现有的主动取证方法通常将深伪检测、篡改定位和来源追踪视为独立任务，缺乏统一的框架来共同解决这些问题。为此，提出了一种统一的主动取证框架，旨在同时处理这三项核心任务。该框架采用了一种创新的152维地标-身份水印（LIDMark），将面部地标与独特的来源标识符结构性地交织在一起。为了稳健地提取LIDMark，设计了一种新型的分解头解码器（FHD），其架构有效地提升了水印的提取性能。
一体化：通过稳健的地标-身份水印统一深伪检测、篡改定位和来源追踪
📄 English Summary
All in One: Unifying Deepfake Detection, Tampering Localization, and Source Tracing with a Robust Landmark-Identity Watermark
The rapid advancement of deepfake technology poses significant threats to personal privacy and social security due to malicious face manipulations. Existing proactive forensic methods typically treat deepfake detection, tampering localization, and source tracing as independent tasks, lacking a unified framework to address them jointly. To bridge this gap, a unified proactive forensics framework is proposed that jointly tackles these three core tasks. The core framework employs an innovative 152-dimensional landmark-identity watermark, termed LIDMark, which structurally interweaves facial landmarks with a unique source identifier. To robustly extract the LIDMark, a novel Factorized-Head Decoder (FHD) is designed, enhancing the performance of watermark extraction.