A Note on Deepfake Detection with Low-Resources
This work addresses the security threat of deepfakes for users with low computational power, but it is incremental as it builds on existing methods like MesoNet.
The paper tackles the problem of deepfake detection for users with limited computational resources by enhancing MesoNet with new activation functions, achieving nearly 1% improvement and higher consistency, and introducing a Local Feature Descriptors method with an Equal Error Rate of 0.28 and accuracy/recall over 0.7.
Deepfakes are videos that include changes, quite often substituting face of a portrayed individual with a different face using neural networks. Even though the technology gained its popularity as a carrier of jokes and parodies it raises a serious threat to ones security - via biometric impersonation or besmearing. In this paper we present two methods that allow detecting Deepfakes for a user without significant computational power. In particular, we enhance MesoNet by replacing the original activation functions allowing a nearly 1% improvement as well as increasing the consistency of the results. Moreover, we introduced and verified a new activation function - Pish that at the cost of slight time overhead allows even higher consistency. Additionally, we present a preliminary results of Deepfake detection method based on Local Feature Descriptors (LFD), that allows setting up the system even faster and without resorting to GPU computation. Our method achieved Equal Error Rate of 0.28, with both accuracy and recall exceeding 0.7.