# FSFM: A Generalizable Face Security Foundation Model via Self-Supervised Facial Representation Learning

arXiv: https://arxiv.org/abs/2412.12032 · HTML: https://mlsanity.com/paper/2412.12032/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 98 of its 139 references that are in the map.
- First posted on arXiv 16 Dec 2024.

## Builds on (most cited first, 30 of 98)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [SimMIM: A Simple Framework for Masked Image Modeling](https://mlsanity.com/paper/2111.09886/) (2021)
- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [iBOT: Image BERT Pre-Training with Online Tokenizer](https://mlsanity.com/paper/2111.07832/) (2021)
- [Masked Feature Prediction for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2112.09133/) (2021)
- [Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics](https://mlsanity.com/paper/1909.12962/) (2019)
- [Detecting Deepfakes with Self-Blended Images](https://mlsanity.com/paper/2204.08376/) (2022)
- [Masked Siamese Networks for Label-Efficient Learning](https://mlsanity.com/paper/2204.07141/) (2022)
- [Context Autoencoder for Self-Supervised Representation Learning](https://mlsanity.com/paper/2202.03026/) (2022)
- [MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis](https://mlsanity.com/paper/2211.09117/) (2022)

## Built on by (most cited first, 23 of 23)

- [Robust Deepfake Detection, NTIRE 2026 Challenge: Report](https://mlsanity.com/paper/2604.24163/) (2026)
- [Who Made This? Fake Detection and Source Attribution with Diffusion Features](https://mlsanity.com/paper/2510.27602/) (2025)
- [Investigating self-supervised representations for audio-visual deepfake detection](https://mlsanity.com/paper/2511.17181/) (2025)
- [Focal-RegionFace: Generating Fine-Grained Multi-attribute Descriptions for Arbitrarily Selected Face Focal Regions](https://mlsanity.com/paper/2601.00156/) (2026)
- [ExposeAnyone: Personalized Audio-to-Expression Diffusion Models Are Robust Zero-Shot Face Forgery Detectors](https://mlsanity.com/paper/2601.02359/) (2026)
- [Leave No Stone Unturned: Uncovering Holistic Audio-Visual Intrinsic Coherence for Deepfake Detection](https://mlsanity.com/paper/2603.23960/) (2026)
- [The Circumplex Degeneracy Behind the Rare-Class Limit in Affect Recognition](https://mlsanity.com/paper/2606.15763/) (2026)
- [A Shared Latent for Partially-Labeled Multi-Task Facial Affect Recognition](https://mlsanity.com/paper/2607.16285/) (2026)
- [Foundation Models for Face Presentation Attack Detection: A Unified Linear-Probing Benchmark](https://mlsanity.com/paper/2607.26993/) (2026)
- [Uncertainty-Aware Deepfake Detection via Multi-View Structural Learning](https://mlsanity.com/paper/2607.28769/) (2026)
- [Improving Generalization in Deepfake Detection with Face Foundation Models and Metric Learning](https://mlsanity.com/paper/2508.19730/) (2025)
- [Beyond Flicker: Detecting Kinematic Inconsistencies for Generalizable Deepfake Video Detection](https://mlsanity.com/paper/2512.04175/) (2025)
- [Na"ive Exposure of Generative AI Capabilities Undermines Deepfake Detection](https://mlsanity.com/paper/2603.10504/) (2026)
- [Domain-generalizable Face Anti-Spoofing with Patch-based Multi-tasking and Artifact Pattern Conversion](https://mlsanity.com/paper/2604.09018/) (2026)
- [The Alpha Blending Hypothesis: Compositing Shortcut in Deepfake Detection](https://mlsanity.com/paper/2605.10334/) (2026)
- [Strength-Parity Ensembling with Parameter-Isolated Experts for Multi-Task Affect Recognition](https://mlsanity.com/paper/2607.16290/) (2026)
- [Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI](https://mlsanity.com/paper/2608.05258/) (2026)
- [LoRA-based Adaptation Alone Is Not Enough: Understanding the Limits of Foundation Models for Face Presentation Attack Detection](https://mlsanity.com/paper/2608.09633/) (2026)
- [Foundation and Multimodal Large Language Models for Face Presentation and Morph Attack Detection](https://mlsanity.com/paper/2608.29802/) (2026)
- [DF26: We Cannot Tell Fake From Real Anymore](https://mlsanity.com/paper/2609.07369/) (2026)
- [Harnessing CLIP and DINO: An Uncertainty-Aware Cascaded Fusion Network for Generalizable Deepfake Image Detection](https://mlsanity.com/paper/2609.07670/) (2026)
- [ForensicZoom: Adaptive Visual Inspection with Multimodal LLMs for Industrial-Grade Face Forgery Detection](https://mlsanity.com/paper/2609.31661/) (2026)
- [DIME: Scaling Facial Representation Learning via Differential Masked Autoencoding](https://mlsanity.com/paper/2610.17015/) (2026)

## Abstract (arXiv)

This work asks: with abundant, unlabeled real faces, how to learn a robust and transferable facial representation that boosts various face security tasks with respect to generalization performance? We make the first attempt and propose a self-supervised pretraining framework to learn fundamental representations of real face images, FSFM, that leverages the synergy between masked image modeling (MIM) and instance discrimination (ID). We explore various facial masking strategies for MIM and present a simple yet powerful CRFR-P masking, which explicitly forces the model to capture meaningful intra-region consistency and challenging inter-region coherency. Furthermore, we devise the ID network that naturally couples with MIM to establish underlying local-to-global correspondence via tailored self-distillation. These three learning objectives, namely 3C, empower encoding both local features and global semantics of real faces. After pretraining, a vanilla ViT serves as a universal vision foundation model for downstream face security tasks: cross-dataset deepfake detection, cross-domain face anti-spoofing, and unseen diffusion facial forgery detection. Extensive experiments on 10 public datasets demonstrate that our model transfers better than supervised pretraining, visual and facial self-supervised learning arts, and even outperforms task-specialized SOTA methods.