# Aggregating Layers for Deepfake Detection

arXiv: https://arxiv.org/abs/2210.05478 · HTML: https://mlsanity.com/paper/2210.05478/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 27 references that are in the map.
- First posted on arXiv 11 Oct 2022.

## Builds on (most cited first, 23 of 23)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [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)
- [Face2Face: Real-time Face Capture and Reenactment of RGB Videos](https://mlsanity.com/paper/2007.14808/) (2020)
- [Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1910.01279/) (2019)
- [Deep Layer Aggregation](https://mlsanity.com/paper/1707.06484/) (2017)
- [Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detection](https://mlsanity.com/paper/2012.07657/) (2020)
- [What makes fake images detectable? Understanding properties that generalize](https://mlsanity.com/paper/2008.10588/) (2020)
- [Deferred Neural Rendering: Image Synthesis using Neural Textures](https://mlsanity.com/paper/1904.12356/) (2019)
- [DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection](https://mlsanity.com/paper/2001.00179/) (2020)
- [Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detection](https://mlsanity.com/paper/2103.09096/) (2021)
- [Two-Stream Neural Networks for Tampered Face Detection](https://mlsanity.com/paper/1803.11276/) (2018)
- [Representative Forgery Mining for Fake Face Detection](https://mlsanity.com/paper/2104.06609/) (2021)
- [On GANs and GMMs](https://mlsanity.com/paper/1805.12462/) (2018)
- [Exposing GAN-generated Faces Using Inconsistent Corneal Specular Highlights](https://mlsanity.com/paper/2009.11924/) (2020)
- [Improving the Efficiency and Robustness of Deepfakes Detection through Precise Geometric Features](https://mlsanity.com/paper/2104.04480/) (2021)
- [Deepfakes Detection with Automatic Face Weighting](https://mlsanity.com/paper/2004.12027/) (2020)
- [Generalized Zero and Few-Shot Transfer for Facial Forgery Detection](https://mlsanity.com/paper/2006.11863/) (2020)

## Built on by (most cited first, 4 of 4)

- [Leveraging Representations from Intermediate Encoder-blocks for Synthetic Image Detection](https://mlsanity.com/paper/2402.19091/) (2024)
- [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)
- [Recent Advancements In The Field Of Deepfake Detection](https://mlsanity.com/paper/2308.05563/) (2023)

## Abstract (arXiv)

The increasing popularity of facial manipulation (Deepfakes) and synthetic face creation raises the need to develop robust forgery detection solutions. Crucially, most work in this domain assume that the Deepfakes in the test set come from the same Deepfake algorithms that were used for training the network. This is not how things work in practice. Instead, we consider the case where the network is trained on one Deepfake algorithm, and tested on Deepfakes generated by another algorithm. Typically, supervised techniques follow a pipeline of visual feature extraction from a deep backbone, followed by a binary classification head. Instead, our algorithm aggregates features extracted across all layers of one backbone network to detect a fake. We evaluate our approach on two domains of interest - Deepfake detection and Synthetic image detection, and find that we achieve SOTA results.