# Where Do Deep Fakes Look? Synthetic Face Detection via Gaze Tracking

arXiv: https://arxiv.org/abs/2101.01165 · HTML: https://mlsanity.com/paper/2101.01165/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 73 references that are in the map.
- First posted on arXiv 4 Jan 2021.

## Builds on (most cited first, 30 of 33)

- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)
- [Face2Face: Real-time Face Capture and Reenactment of RGB Videos](https://mlsanity.com/paper/2007.14808/) (2020)
- [Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics](https://mlsanity.com/paper/1909.12962/) (2019)
- [MesoNet: a Compact Facial Video Forgery Detection Network](https://mlsanity.com/paper/1809.00888/) (2018)
- [Video-to-Video Synthesis](https://mlsanity.com/paper/1808.06601/) (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)
- [Deep Video Portraits](https://mlsanity.com/paper/1805.11714/) (2018)
- [DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection](https://mlsanity.com/paper/2001.03024/) (2020)
- [Deferred Neural Rendering: Image Synthesis using Neural Textures](https://mlsanity.com/paper/1904.12356/) (2019)
- [The Creation and Detection of Deepfakes: A Survey](https://mlsanity.com/paper/2004.11138/) (2020)
- [Capsule-Forensics: Using Capsule Networks to Detect Forged Images and Videos](https://mlsanity.com/paper/1810.11215/) (2018)
- [Deep Pyramidal Residual Networks](https://mlsanity.com/paper/1610.02915/) (2016)
- [Eye Tracking for Everyone](https://mlsanity.com/paper/1606.05814/) (2016)
- [FakeCatcher: Detection of Synthetic Portrait Videos using Biological Signals](https://mlsanity.com/paper/1901.02212/) (2019)
- [Two-Stream Neural Networks for Tampered Face Detection](https://mlsanity.com/paper/1803.11276/) (2018)
- [MPIIGaze: Real-World Dataset and Deep Appearance-Based Gaze Estimation](https://mlsanity.com/paper/1711.09017/) (2017)
- [Emotions Don't Lie: An Audio-Visual Deepfake Detection Method Using Affective Cues](https://mlsanity.com/paper/2003.06711/) (2020)
- [Learning Formation of Physically-Based Face Attributes](https://mlsanity.com/paper/2004.03458/) (2020)
- [Generative Face Completion](https://mlsanity.com/paper/1704.05838/) (2017)
- [Adversarial Deepfakes: Evaluating Vulnerability of Deepfake Detectors to Adversarial Examples](https://mlsanity.com/paper/2002.12749/) (2020)
- [Exposing GAN-generated Faces Using Inconsistent Corneal Specular Highlights](https://mlsanity.com/paper/2009.11924/) (2020)
- [In Ictu Oculi: Exposing AI Generated Fake Face Videos by Detecting Eye Blinking](https://mlsanity.com/paper/1806.02877/) (2018)
- [Rendering of Eyes for Eye-Shape Registration and Gaze Estimation](https://mlsanity.com/paper/1505.05916/) (2015)
- [ExprGAN: Facial Expression Editing with Controllable Expression Intensity](https://mlsanity.com/paper/1709.03842/) (2017)
- [Pupil: An Open Source Platform for Pervasive Eye Tracking and Mobile Gaze-based Interaction](https://mlsanity.com/paper/1405.0006/) (2014)
- [Understanding the Disharmony between Dropout and Batch Normalization by Variance Shift](https://mlsanity.com/paper/1801.05134/) (2018)

## Built on by (most cited first, 9 of 9)

- [Generalizable Deepfake Detection with Phase-Based Motion Analysis](https://mlsanity.com/paper/2211.09363/) (2022)
- [Using Deep Learning to Detecting Deepfakes](https://mlsanity.com/paper/2207.13644/) (2022)
- [How Do Deepfakes Move? Motion Magnification for Deepfake Source Detection](https://mlsanity.com/paper/2212.14033/) (2022)
- [Introducing Explicit Gaze Constraints to Face Swapping](https://mlsanity.com/paper/2305.16138/) (2023)
- [GazeForensics: DeepFake Detection via Gaze-guided Spatial Inconsistency Learning](https://mlsanity.com/paper/2311.07075/) (2023)
- [DeepFakes: Detecting Forged and Synthetic Media Content Using Machine Learning](https://mlsanity.com/paper/2109.02874/) (2021)
- [Towards mitigating uncann(eye)ness in face swaps via gaze-centric loss terms](https://mlsanity.com/paper/2402.03188/) (2024)
- [Is It Certainly a Deepfake? Reliability Analysis in Detection & Generation Ecosystem](https://mlsanity.com/paper/2509.17550/) (2025)
- [DeepFake Detection in Dyadic Video Calls using Point of Gaze Tracking](https://mlsanity.com/paper/2509.25503/) (2025)

## Abstract (arXiv)

Following the recent initiatives for the democratization of AI, deep fake generators have become increasingly popular and accessible, causing dystopian scenarios towards social erosion of trust. A particular domain, such as biological signals, attracted attention towards detection methods that are capable of exploiting authenticity signatures in real videos that are not yet faked by generative approaches. In this paper, we first propose several prominent eye and gaze features that deep fakes exhibit differently. Second, we compile those features into signatures and analyze and compare those of real and fake videos, formulating geometric, visual, metric, temporal, and spectral variations. Third, we generalize this formulation to the deep fake detection problem by a deep neural network, to classify any video in the wild as fake or real. We evaluate our approach on several deep fake datasets, achieving 92.48% accuracy on FaceForensics++, 80.0% on Deep Fakes (in the wild), 88.35% on CelebDF, and 99.27% on DeeperForensics datasets. Our approach outperforms most deep and biological fake detectors with complex network architectures without the proposed gaze signatures. We conduct ablation studies involving different features, architectures, sequence durations, and post-processing artifacts.