CausalVE：基于因果视频预测的人脸视频隐私加密
CausalVE: Face Video Privacy Encryption via Causal Video Prediction
AI总结：
本文提出神经网络框架 CausalVE，结合扩散模型换脸、因果视频预测和可逆神经网络视频隐藏，实现人脸视频隐私保护与秘密数据传播，实验表明其在安全性上优于现有方法。
摘要：
先进的人脸识别技术和推荐系统在人脸交互方面缺乏充分的隐私保护技术与政策，这加剧了人们对生物隐私侵犯的担忧。随着视频和直播网站的普及，公开人脸视频的传播与交互带来了更大的隐私风险。现有技术通常通过各种隐私增强方法来应对敏感生物特征信息泄露的风险，但要么破坏了交互数据所要传达的信息，从而带来更高的安全风险，要么保留了某些生物特征，使攻击者能够从中推断出敏感的生物特征信息。为了解决这些不足，本文提出了一个神经网络框架 CausalVE。我们采用扩散模型在人脸引导下实现换脸，从而获得封面图像，并利用秘密视频的语音序列特征和时空序列特征进行动态视频推理与预测，得到与秘密视频帧数相同的封面视频。此外，我们使用可逆神经网络进行视频隐藏来隐藏秘密视频，使视频同时能够传播秘密数据。大量实验证明，我们的 CausalVE 在公开视频传播中具有良好的安全性，并在定性、定量和视觉角度上优于最先进的方法。
英文摘要：
Advanced facial recognition technologies and recommender systems with inadequate privacy technologies and policies for facial interactions increase concerns about bioprivacy violations. With the proliferation of video and live-streaming websites, public-face video distribution and interactions pose greater privacy risks. Existing techniques typically address the risk of sensitive biometric information leakage through various privacy enhancement methods but pose a higher security risk by corrupting the information to be conveyed by the interaction data, or by leaving certain biometric features intact that allow an attacker to infer sensitive biometric information from them. To address these shortcomings, in this paper, we propose a neural network framework, CausalVE. We obtain cover images by adopting a diffusion model to achieve face swapping with face guidance and use the speech sequence features and spatiotemporal sequence features of the secret video for dynamic video inference and prediction to obtain a cover video with the same number of frames as the secret video. In addition, we hide the secret video by using reversible neural networks for video hiding so that the video can also disseminate secret data. Numerous experiments prove that our CausalVE has good security in public video dissemination and outperforms state-of-the-art methods from a qualitative, quantitative, and visual point of view.
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。
