# What's wrong with this video? Comparing Explainers for Deepfake Detection

arXiv: https://arxiv.org/abs/2105.05902 · HTML: https://mlsanity.com/paper/2105.05902/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 39 references that are in the map.
- First posted on arXiv 12 May 2021.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [Albumentations: fast and flexible image augmentations](https://mlsanity.com/paper/1809.06839/) (2018)
- [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)
- [Exposing DeepFake Videos By Detecting Face Warping Artifacts](https://mlsanity.com/paper/1811.00656/) (2018)
- [Exposing Deep Fakes Using Inconsistent Head Poses](https://mlsanity.com/paper/1811.00661/) (2018)
- [On the Detection of Digital Face Manipulation](https://mlsanity.com/paper/1910.01717/) (2019)
- [DeepFakes: a New Threat to Face Recognition? Assessment and Detection](https://mlsanity.com/paper/1812.08685/) (2018)
- [Capsule-Forensics: Using Capsule Networks to Detect Forged Images and Videos](https://mlsanity.com/paper/1810.11215/) (2018)
- [Multi-task Learning For Detecting and Segmenting Manipulated Facial Images and Videos](https://mlsanity.com/paper/1906.06876/) (2019)
- [Recurrent Convolutional Strategies for Face Manipulation Detection in Videos](https://mlsanity.com/paper/1905.00582/) (2019)
- [Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey](https://mlsanity.com/paper/1911.12116/) (2019)
- [Learn To Pay Attention](https://mlsanity.com/paper/1804.02391/) (2018)
- [DeepFake Detection by Analyzing Convolutional Traces](https://mlsanity.com/paper/2004.10448/) (2020)
- [BlazeFace: Sub-millisecond Neural Face Detection on Mobile GPUs](https://mlsanity.com/paper/1907.05047/) (2019)
- [Video Face Manipulation Detection Through Ensemble of CNNs](https://mlsanity.com/paper/2004.07676/) (2020)
- [In Ictu Oculi: Exposing AI Generated Fake Face Videos by Detecting Eye Blinking](https://mlsanity.com/paper/1806.02877/) (2018)

## Built on by (most cited first, 3 of 3)

- [Quantitative Metrics for Evaluating Explanations of Video DeepFake Detectors](https://mlsanity.com/paper/2210.03683/) (2022)
- [Improving the Perturbation-Based Explanation of Deepfake Detectors Through the Use of Adversarially-Generated Samples](https://mlsanity.com/paper/2502.03957/) (2025)
- [LayLens: Improving Deepfake Understanding through Simplified Explanations](https://mlsanity.com/paper/2507.10066/) (2025)

## Abstract (arXiv)

Deepfakes are computer manipulated videos where the face of an individual has been replaced with that of another. Software for creating such forgeries is easy to use and ever more popular, causing serious threats to personal reputation and public security. The quality of classifiers for detecting deepfakes has improved with the releasing of ever larger datasets, but the understanding of why a particular video has been labelled as fake has not kept pace. In this work we develop, extend and compare white-box, black-box and model-specific techniques for explaining the labelling of real and fake videos. In particular, we adapt SHAP, GradCAM and self-attention models to the task of explaining the predictions of state-of-the-art detectors based on EfficientNet, trained on the Deepfake Detection Challenge (DFDC) dataset. We compare the obtained explanations, proposing metrics to quantify their visual features and desirable characteristics, and also perform a user survey collecting users' opinions regarding the usefulness of the explainers.