GAN-Generated Faces Detection: A Survey and New Perspectives

Abstract

Generative Adversarial Networks (GAN) have led to the generation of very realistic face images, which have been used in fake social media accounts and other disinformation matters that can generate profound impacts. Therefore, the corresponding GAN-face detection techniques are under active development that can examine and expose such fake faces. In this work, we aim to provide a comprehensive review of recent progress in GAN-face detection. We focus on methods that can detect face images that are generated or synthesized from GAN models. We classify the existing detection works into four categories: (1) deep learning-based, (2) physical-based, (3) physiological-based methods, and (4) evaluation and comparison against human visual performance. For each category, we summarize the key ideas and connect them with method implementations. We also discuss open problems and suggest future research directions.

Few-Shot Learning for Misinformation Detection Based on Contrastive Models

“…Detecting fake news and misinformation is a critical challenge in today's proliferation of social media, and there is a growing need for accurate and efficient approaches to address this issue [7]. Manual fact-checking is time-consuming and labor-intensive [8]. For this reason, various automatic approaches have been developed to combat fake news, such as those utilizing machine learning techniques like supervised classification models [8][9][10][11][12][13].…”

“…Manual fact-checking is time-consuming and labor-intensive [8]. For this reason, various automatic approaches have been developed to combat fake news, such as those utilizing machine learning techniques like supervised classification models [8][9][10][11][12][13]. However, these models are mainly required to take advantage of high-quality labeled data, which may be scarce and not cover the full diversity of fake news content.…”