# Learning to Detect Fake Face Images in the Wild

arXiv: https://arxiv.org/abs/1809.08754 · HTML: https://mlsanity.com/paper/1809.08754/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Sep 2018.

## Built on by (most cited first, 22 of 22)

- [Exploring Temporal Coherence for More General Video Face Forgery Detection](https://mlsanity.com/paper/2108.06693/) (2021)
- [Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization](https://mlsanity.com/paper/2210.14457/) (2022)
- [AltFreezing for More General Video Face Forgery Detection](https://mlsanity.com/paper/2307.08317/) (2023)
- [Deepfake Generation and Detection: A Benchmark and Survey](https://mlsanity.com/paper/2403.17881/) (2024)
- [Countering Malicious DeepFakes: Survey, Battleground, and Horizon](https://mlsanity.com/paper/2103.00218/) (2021)
- [MINTIME: Multi-Identity Size-Invariant Video Deepfake Detection](https://mlsanity.com/paper/2211.10996/) (2022)
- [A Review of Deep Learning-based Approaches for Deepfake Content Detection](https://mlsanity.com/paper/2202.06095/) (2022)
- [Beyond Spatial Frequency: Pixel-wise Temporal Frequency-based Deepfake Video Detection](https://mlsanity.com/paper/2507.02398/) (2025)
- [Pattern Detection in the Activation Space for Identifying Synthesized Content](https://mlsanity.com/paper/2105.12479/) (2021)
- [Detecting Localized Deepfake Manipulations Using Action Unit-Guided Video Representations](https://mlsanity.com/paper/2503.22121/) (2025)
- [Fighting Malicious Media Data: A Survey on Tampering Detection and Deepfake Detection](https://mlsanity.com/paper/2212.05667/) (2022)
- [Data-Agnostic Face Image Synthesis Detection Using Bayesian CNNs](https://mlsanity.com/paper/2401.04241/) (2024)
- [ALBERT: Advanced Localization and Bidirectional Encoder Representations from Transformers for Automotive Damage Evaluation](https://mlsanity.com/paper/2506.10524/) (2025)
- [Sequential training of GANs against GAN-classifiers reveals correlated "knowledge gaps" present among independently trained GAN instances](https://mlsanity.com/paper/2303.15533/) (2023)
- [GRACE: Graph-Regularized Attentive Convolutional Entanglement with Laplacian Smoothing for Robust DeepFake Video Detection](https://mlsanity.com/paper/2406.19941/) (2024)
- [VIPPrint: A Large Scale Dataset of Printed and Scanned Images for Synthetic Face Images Detection and Source Linking](https://mlsanity.com/paper/2102.06792/) (2021)
- [Transferable Class-Modelling for Decentralized Source Attribution of GAN-Generated Images](https://mlsanity.com/paper/2203.09777/) (2022)
- [Deepfake Detection using Biological Features: A Survey](https://mlsanity.com/paper/2301.05819/) (2023)
- [Deepfake Detection of Occluded Images Using a Patch-based Approach](https://mlsanity.com/paper/2304.04537/) (2023)
- [Detecting Face Synthesis Using a Concealed Fusion Model](https://mlsanity.com/paper/2401.04257/) (2024)
- [AI, Entrepreneurs, and Privacy: Deep Learning Outperforms Humans in Detecting Entrepreneurs from Image Data](https://mlsanity.com/paper/2409.03765/) (2024)
- [Towards Robust DeepFake Detection under Unstable Face Sequences: Adaptive Sparse Graph Embedding with Order-Free Representation and Explicit Laplacian Spectral Prior](https://mlsanity.com/paper/2512.07498/) (2025)

## Abstract (arXiv)

Although Generative Adversarial Network (GAN) can be used to generate the realistic image, improper use of these technologies brings hidden concerns. For example, GAN can be used to generate a tampered video for specific people and inappropriate events, creating images that are detrimental to a particular person, and may even affect that personal safety. In this paper, we will develop a deep forgery discriminator (DeepFD) to efficiently and effectively detect the computer-generated images. Directly learning a binary classifier is relatively tricky since it is hard to find the common discriminative features for judging the fake images generated from different GANs. To address this shortcoming, we adopt contrastive loss in seeking the typical features of the synthesized images generated by different GANs and follow by concatenating a classifier to detect such computer-generated images. Experimental results demonstrate that the proposed DeepFD successfully detected 94.7% fake images generated by several state-of-the-art GANs.