DistilDIRE: A Small, Fast, Cheap and Lightweight Diffusion Synthesized Deepfake Detection
This work addresses the need for efficient deepfake detection in real-world applications, though it appears incremental as it builds on the DIRE framework.
The paper tackles the problem of detecting diffusion-generated deepfake images, which is computationally expensive using existing methods like DIRE, and proposes a distilled model that achieves inference speeds 3.2 times faster while maintaining robust performance.
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.