# On Improving Cross-dataset Generalization of Deepfake Detectors

arXiv: https://arxiv.org/abs/2204.04285 · HTML: https://mlsanity.com/paper/2204.04285/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 36 references that are in the map.
- First posted on arXiv 8 Apr 2022.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [AutoAugment: Learning Augmentation Policies from Data](https://mlsanity.com/paper/1805.09501/) (2018)
- [Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics](https://mlsanity.com/paper/1909.12962/) (2019)
- [Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues](https://mlsanity.com/paper/2007.09355/) (2020)
- [A Brief Survey of Deep Reinforcement Learning](https://mlsanity.com/paper/1708.05866/) (2017)
- [Face X-ray for More General Face Forgery Detection](https://mlsanity.com/paper/1912.13458/) (2019)
- [MesoNet: a Compact Facial Video Forgery Detection Network](https://mlsanity.com/paper/1809.00888/) (2018)
- [Multi-attentional Deepfake Detection](https://mlsanity.com/paper/2103.02406/) (2021)
- [Exposing DeepFake Videos By Detecting Face Warping Artifacts](https://mlsanity.com/paper/1811.00656/) (2018)
- [DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection](https://mlsanity.com/paper/2001.03024/) (2020)
- [DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection](https://mlsanity.com/paper/2001.00179/) (2020)
- [FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping](https://mlsanity.com/paper/1912.13457/) (2019)
- [Two-branch Recurrent Network for Isolating Deepfakes in Videos](https://mlsanity.com/paper/2008.03412/) (2020)
- [Multi-task Learning For Detecting and Segmenting Manipulated Facial Images and Videos](https://mlsanity.com/paper/1906.06876/) (2019)
- [Two-Stream Neural Networks for Tampered Face Detection](https://mlsanity.com/paper/1803.11276/) (2018)
- [Fast Face-swap Using Convolutional Neural Networks](https://mlsanity.com/paper/1611.09577/) (2016)
- [Detecting Deep-Fake Videos from Appearance and Behavior](https://mlsanity.com/paper/2004.14491/) (2020)
- [Identity-Driven DeepFake Detection](https://mlsanity.com/paper/2012.03930/) (2020)
- [An Experimental Evaluation on Deepfake Detection using Deep Face Recognition](https://mlsanity.com/paper/2110.01640/) (2021)

## Built on by (most cited first, 30 of 34)

- [Improving Fairness in Deepfake Detection](https://mlsanity.com/paper/2306.16635/) (2023)
- [GBDF: Gender Balanced DeepFake Dataset Towards Fair DeepFake Detection](https://mlsanity.com/paper/2207.10246/) (2022)
- [Fake It till You Make It: Curricular Dynamic Forgery Augmentations towards General Deepfake Detection](https://mlsanity.com/paper/2409.14444/) (2024)
- [Controllable Guide-Space for Generalizable Face Forgery Detection](https://mlsanity.com/paper/2307.14039/) (2023)
- [How well are open sourced AI-generated image detection models out-of-the-box: A comprehensive benchmark study](https://mlsanity.com/paper/2602.07814/) (2026)
- [A Survey of Defenses Against AI-Generated Visual Media: Detection,Disruption, and Authentication](https://mlsanity.com/paper/2407.10575/) (2024)
- [Delocate: Detection and Localization for Deepfake Videos with Randomly-Located Tampered Traces](https://mlsanity.com/paper/2401.13516/) (2024)
- [An Examination of Bias of Facial Analysis based BMI Prediction Models](https://mlsanity.com/paper/2204.10262/) (2022)
- [Joint Physical-Digital Facial Attack Detection Via Simulating Spoofing Clues](https://mlsanity.com/paper/2404.08450/) (2024)
- [CrossDF: Improving Cross-Domain Deepfake Detection with Deep Information Decomposition](https://mlsanity.com/paper/2310.00359/) (2023)
- [Social Media Authentication and Combating Deepfakes using Semi-fragile Invisible Image Watermarking](https://mlsanity.com/paper/2410.01906/) (2024)
- [Cross-Corpora Spoken Language Identification with Domain Diversification and Generalization](https://mlsanity.com/paper/2302.05110/) (2023)
- [Undercover Deepfakes: Detecting Fake Segments in Videos](https://mlsanity.com/paper/2305.06564/) (2023)
- [Face2Parts: Exploring Coarse-to-Fine Inter-Regional Facial Dependencies for Generalized Deepfake Detection](https://mlsanity.com/paper/2603.26036/) (2026)
- [Shaking the Fake: Detecting Deepfake Videos in Real Time via Active Probes](https://mlsanity.com/paper/2409.10889/) (2024)
- [D2Fusion: Dual-domain Fusion with Feature Superposition for Deepfake Detection](https://mlsanity.com/paper/2503.17184/) (2025)
- [MFFI: Multi-Dimensional Face Forgery Image Dataset for Real-World Scenarios](https://mlsanity.com/paper/2509.05592/) (2025)
- [Mover: Mask and Recovery based Facial Part Consistency Aware Method for Deepfake Video Detection](https://mlsanity.com/paper/2303.01740/) (2023)
- [Leveraging Deep Learning Approaches for Deepfake Detection: A Review](https://mlsanity.com/paper/2304.01908/) (2023)
- [Attention Consistency Refined Masked Frequency Forgery Representation for Generalizing Face Forgery Detection](https://mlsanity.com/paper/2307.11438/) (2023)
- [Recoverable Privacy-Preserving Image Classification through Noise-like Adversarial Examples](https://mlsanity.com/paper/2310.12707/) (2023)
- [FSBI: Deepfakes Detection with Frequency Enhanced Self-Blended Images](https://mlsanity.com/paper/2406.08625/) (2024)
- [Tex-ViT: A Generalizable, Robust, Texture-based dual-branch cross-attention deepfake detector](https://mlsanity.com/paper/2408.16892/) (2024)
- [Facial Forgery-based Deepfake Detection using Fine-Grained Features](https://mlsanity.com/paper/2310.07028/) (2023)
- [Cross-Branch Orthogonality for Improved Generalization in Face Deepfake Detection](https://mlsanity.com/paper/2505.04888/) (2025)
- [A Hybrid Deep Learning and Forensic Approach for Robust Deepfake Detection](https://mlsanity.com/paper/2510.27392/) (2025)
- [Your AI-Generated Image Detector Can Secretly Achieve SOTA Accuracy, If Calibrated](https://mlsanity.com/paper/2602.01973/) (2026)
- [A Siamese-based Verification System for Open-set Architecture Attribution of Synthetic Images](https://mlsanity.com/paper/2307.09822/) (2023)
- [Recap: Detecting Deepfake Video with Unpredictable Tampered Traces via Recovering Faces and Mapping Recovered Faces](https://mlsanity.com/paper/2308.09921/) (2023)
- [Open Set Face Forgery Detection via Dual-Level Evidence Collection](https://mlsanity.com/paper/2512.04331/) (2025)

## Abstract (arXiv)

Facial manipulation by deep fake has caused major security risks and raised severe societal concerns. As a countermeasure, a number of deep fake detection methods have been proposed recently. Most of them model deep fake detection as a binary classification problem using a backbone convolutional neural network (CNN) architecture pretrained for the task. These CNN-based methods have demonstrated very high efficacy in deep fake detection with the Area under the Curve (AUC) as high as 0.99. However, the performance of these methods degrades significantly when evaluated across datasets. In this paper, we formulate deep fake detection as a hybrid combination of supervised and reinforcement learning (RL) to improve its cross-dataset generalization performance. The proposed method chooses the top-k augmentations for each test sample by an RL agent in an image-specific manner. The classification scores, obtained using CNN, of all the augmentations of each test image are averaged together for final real or fake classification. Through extensive experimental validation, we demonstrate the superiority of our method over existing published research in cross-dataset generalization of deep fake detectors, thus obtaining state-of-the-art performance.