DistilDIRE：一种小型、快速、廉价且轻量级的扩散合成深度伪造检测。

DistilDIRE: A Small, Fast, Cheap and Lightweight Diffusion Synthesized Deepfake Detection

June 2, 2024

作者: Yewon Lim, Changyeon Lee, Aerin Kim, Oren Etzioni

cs.AI

摘要

近年来，扩散生成的图像数量急剧增加，给当前的检测技术带来了独特挑战。虽然识别这些图像的任务属于二元分类，看似简单的类别，但采用“重建再比较”技术时的计算负荷是巨大的。这种方法被称为DIRE（扩散重建误差），不仅可以识别扩散生成的图像，还可以检测由GANs生成的图像，突显了该技术的广泛适用性。为了解决计算挑战并提高效率，我们提出提炼扩散模型中嵌入的知识，开发快速深度伪造检测模型。我们的方法旨在创建一个小型、快速、廉价且轻量级的扩散合成深度伪造检测器，保持强大性能的同时显著降低运行需求。根据我们的实验结果表明，我们的推理速度比现有的DIRE框架快3.2倍。这一进展不仅增强了在实际环境中部署这些系统的实用性，还为未来旨在利用扩散模型知识的研究努力铺平了道路。

English

A dramatic influx of diffusion-generated images has marked recent years, posing unique challenges to current detection technologies. While the task of identifying these images falls under binary classification, a seemingly straightforward category, the computational load is significant when employing the "reconstruction then compare" technique. This approach, known as DIRE (Diffusion Reconstruction Error), not only identifies diffusion-generated images but also detects those produced by GANs, highlighting the technique's broad applicability. To address the computational challenges and improve efficiency, we propose distilling the knowledge embedded in diffusion models to develop rapid deepfake detection models. Our approach, aimed at creating a small, fast, cheap, and lightweight diffusion synthesized deepfake detector, maintains robust performance while significantly reducing operational demands. Maintaining performance, our experimental results indicate an inference speed 3.2 times faster than the existing DIRE framework. This advance not only enhances the practicality of deploying these systems in real-world settings but also paves the way for future research endeavors that seek to leverage diffusion model knowledge.