# Deepfake Detection in Social Media: A Temporal Artifact Analysis Using 3D Convolutional Neural Networks

arXiv: https://arxiv.org/abs/2605.17573 · HTML: https://mlsanity.com/paper/2605.17573/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 32 references that are in the map.
- First posted on arXiv 17 May 2026.

## Builds on (most cited first, 25 of 25)

- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- [DF40: Toward Next-Generation Deepfake Detection](https://mlsanity.com/paper/2406.13495/) (2024)
- [Recurrent Convolutional Strategies for Face Manipulation Detection in Videos](https://mlsanity.com/paper/1905.00582/) (2019)
- [AVFF: Audio-Visual Feature Fusion for Video Deepfake Detection](https://mlsanity.com/paper/2406.02951/) (2024)
- [Generalizing Deepfake Video Detection with Plug-and-Play: Video-Level Blending and Spatiotemporal Adapter Tuning](https://mlsanity.com/paper/2408.17065/) (2024)
- [Real-Time Deepfake Detection in the Real-World](https://mlsanity.com/paper/2406.09398/) (2024)
- [Towards More General Video-based Deepfake Detection through Facial Component Guided Adaptation for Foundation Model](https://mlsanity.com/paper/2404.05583/) (2024)
- [Faster Than Lies: Real-time Deepfake Detection using Binary Neural Networks](https://mlsanity.com/paper/2406.04932/) (2024)
- [Learning Natural Consistency Representation for Face Forgery Video Detection](https://mlsanity.com/paper/2407.10550/) (2024)
- [Frequency-Aware Deepfake Detection: Improving Generalizability through Frequency Space Learning](https://mlsanity.com/paper/2403.07240/) (2024)
- [Exploring Self-Supervised Vision Transformers for Deepfake Detection: A Comparative Analysis](https://mlsanity.com/paper/2405.00355/) (2024)
- [A Timely Survey on Vision Transformer for Deepfake Detection](https://mlsanity.com/paper/2405.08463/) (2024)
- [Vulnerability-Aware Spatio-Temporal Learning for Generalizable Deepfake Video Detection](https://mlsanity.com/paper/2501.01184/) (2025)
- [Wavelet-Driven Generalizable Framework for Deepfake Face Forgery Detection](https://mlsanity.com/paper/2409.18301/) (2024)
- [Evolving from Single-modal to Multi-modal Facial Deepfake Detection: Progress and Challenges](https://mlsanity.com/paper/2406.06965/) (2024)
- [Contextual Cross-Modal Attention for Audio-Visual Deepfake Detection and Localization](https://mlsanity.com/paper/2408.01532/) (2024)
- [FakeFormer: Efficient Vulnerability-Driven Transformers for Generalisable Deepfake Detection](https://mlsanity.com/paper/2410.21964/) (2024)
- [Compressed Deepfake Video Detection Based on 3D Spatiotemporal Trajectories](https://mlsanity.com/paper/2404.18149/) (2024)
- [Adaptive Meta-Learning for Robust Deepfake Detection: A Multi-Agent Framework to Data Drift and Model Generalization](https://mlsanity.com/paper/2411.08148/) (2024)
- [HFMF: Hierarchical Fusion Meets Multi-Stream Models for Deepfake Detection](https://mlsanity.com/paper/2501.05631/) (2025)
- [UniForensics: Face Forgery Detection via General Facial Representation](https://mlsanity.com/paper/2407.19079/) (2024)
- [A Multimodal Framework for Deepfake Detection](https://mlsanity.com/paper/2410.03487/) (2024)
- [Reduced Spatial Dependency for More General Video-level Deepfake Detection](https://mlsanity.com/paper/2503.03270/) (2025)
- [FAME: A Lightweight Spatio-Temporal Network for Model Attribution of Face-Swap Deepfakes](https://mlsanity.com/paper/2506.11477/) (2025)

## Abstract (arXiv)

Synthetic facial videos have proliferated across social media faster than platform moderation can respond, raising the cost of disinformation and identity-based attacks. Frame-level deepfake detectors degrade sharply as generator quality increases; high-quality 128x128 GAN output cuts spatial-only accuracy by five percentage points while leaving temporal inconsistencies largely intact. We address this gap with a 3D Convolutional Neural Network detector based on R3D-18, trained with a composite loss that combines binary cross-entropy with a temporal-consistency regularizer. The model processes 16-frame clips from the DeepfakeTIMIT dataset and is initialized from Kinetics-400 action-recognition weights. We report 92.8% accuracy on intra-dataset evaluation at 128x128 resolution; cross-dataset transfer to FaceForensics++ without fine-tuning reaches 76.4%, rising after minimal fine-tuning. Ablation studies show that transfer learning contributes 7.2 percentage points and face tracking adds 3.5 points, while temporal consistency regularization provides additional gains on high-quality fakes. The results establish that temporal artifacts generalize more broadly than spatial ones, providing a detection signal that survives social-media re-encoding.