DEEPFAKE CLI: Accelerated Deepfake Detection using FPGAs

TL;DR

This paper introduces a novel FPGA-accelerated deepfake detection framework called DEEPFAKE C-L-I, achieving high inference speed and accuracy, addressing the challenge of real-time deepfake detection on social media videos.

Contribution

It presents a new FPGA-based acceleration method for deepfake detection using a lightweight model, significantly improving inference speed while maintaining high accuracy.

Findings

Achieved 316.8 FPS on VCK5000 FPGA

Maintained 93% detection accuracy

Demonstrated FPGA's energy efficiency and parallelism advantages

Abstract

Because of the availability of larger datasets and recent improvements in the generative model, more realistic Deepfake videos are being produced each day. People consume around one billion hours of video on social media platforms every day, and thats why it is very important to stop the spread of fake videos as they can be damaging, dangerous, and malicious. There has been a significant improvement in the field of deepfake classification, but deepfake detection and inference have remained a difficult task. To solve this problem in this paper, we propose a novel DEEPFAKE C-L-I (Classification-Localization-Inference) in which we have explored the idea of accelerating Quantized Deepfake Detection Models using FPGAs due to their ability of maximum parallelism and energy efficiency compared to generalized GPUs. In this paper, we have used light MesoNet with EFF-YNet structure and accelerated it on VCK5000 FPGA, powered by state-of-the-art VC1902 Versal Architecture which uses AI, DSP, and Adaptable Engines for acceleration. We have benchmarked our inference speed with other state-of-the-art inference nodes, got 316.8 FPS on VCK5000 while maintaining 93\% Accuracy.