Detecting Deepfake Videos: An Analysis of Three Techniques
This work addresses the detection of manipulated media for security and privacy applications, but it appears incremental as it builds on existing methods from a competition.
The paper tackled the problem of detecting deepfake videos by analyzing three techniques, finding that the grayscale histogram method was more relevant than convolutional LSTM and eye blink detection.
Recent advances in deepfake generating algorithms that produce manipulated media have had dangerous implications in privacy, security and mass communication. Efforts to combat this issue have risen in the form of competitions and funding for research to detect deepfakes. This paper presents three techniques and algorithms: convolutional LSTM, eye blink detection and grayscale histograms-pursued while participating in the Deepfake Detection Challenge. We assessed the current knowledge about deepfake videos, a more severe version of manipulated media, and previous methods used, and found relevance in the grayscale histogram technique over others. We discussed the implications of each method developed and provided further steps to improve the given findings.