# FakeChain: Exposing Shallow Cues in Multi-Step Deepfake Detection

arXiv: https://arxiv.org/abs/2509.16602 · HTML: https://mlsanity.com/paper/2509.16602/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 74 references that are in the map.
- First posted on arXiv 20 Sep 2025.

## Builds on (most cited first, 30 of 41)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- [Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics](https://mlsanity.com/paper/1909.12962/) (2019)
- [Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues](https://mlsanity.com/paper/2007.09355/) (2020)
- [Leveraging Frequency Analysis for Deep Fake Image Recognition](https://mlsanity.com/paper/2003.08685/) (2020)
- [Multi-attentional Deepfake Detection](https://mlsanity.com/paper/2103.02406/) (2021)
- [Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral Distributions](https://mlsanity.com/paper/2003.01826/) (2020)
- [SimSwap: An Efficient Framework For High Fidelity Face Swapping](https://mlsanity.com/paper/2106.06340/) (2021)
- [FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset](https://mlsanity.com/paper/2108.05080/) (2021)
- [StyleSwin: Transformer-based GAN for High-resolution Image Generation](https://mlsanity.com/paper/2112.10762/) (2021)
- [Combining EfficientNet and Vision Transformers for Video Deepfake Detection](https://mlsanity.com/paper/2107.02612/) (2021)
- [Deepfake Generation and Detection: A Benchmark and Survey](https://mlsanity.com/paper/2403.17881/) (2024)
- [ADD: Frequency Attention and Multi-View based Knowledge Distillation to Detect Low-Quality Compressed Deepfake Images](https://mlsanity.com/paper/2112.03553/) (2021)
- [GANprintR: Improved Fakes and Evaluation of the State of the Art in Face Manipulation Detection](https://mlsanity.com/paper/1911.05351/) (2019)
- [CoReD: Generalizing Fake Media Detection with Continual Representation using Distillation](https://mlsanity.com/paper/2107.02408/) (2021)
- [Detecting and Recovering Sequential DeepFake Manipulation](https://mlsanity.com/paper/2207.02204/) (2022)
- [One Detector to Rule Them All: Towards a General Deepfake Attack Detection Framework](https://mlsanity.com/paper/2105.00187/) (2021)
- [Quality-Agnostic Deepfake Detection with Intra-model Collaborative Learning](https://mlsanity.com/paper/2309.05911/) (2023)
- [DiffusionFake: Enhancing Generalization in Deepfake Detection via Guided Stable Diffusion](https://mlsanity.com/paper/2410.04372/) (2024)
- [T-GD: Transferable GAN-generated Images Detection Framework](https://mlsanity.com/paper/2008.04115/) (2020)
- [FaceController: Controllable Attribute Editing for Face in the Wild](https://mlsanity.com/paper/2102.11464/) (2021)
- [FDFtNet: Facing Off Fake Images using Fake Detection Fine-tuning Network](https://mlsanity.com/paper/2001.01265/) (2020)

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

- [Through the Lens: Benchmarking Deepfake Detectors Against Moir'e-Induced Distortions](https://mlsanity.com/paper/2510.23225/) (2025)
- [Detecting AI-Generated Video: A Vision-Language Dual-View Survey](https://mlsanity.com/paper/2607.10787/) (2026)
- [Multi-Tool Image Editing Attribution in Facial Forgery](https://mlsanity.com/paper/2609.02751/) (2026)

## Abstract (arXiv)

Multi-step or hybrid deepfakes, created by sequentially applying different deepfake creation methods such as Face-Swapping, GAN-based generation, and Diffusion methods, can pose an emerging and unforseen technical challenge for detection models trained on single-step forgeries. While prior studies have mainly focused on detecting isolated single manipulation, little is known about the detection model behavior under such compositional, hybrid, and complex manipulation pipelines. In this work, we introduce FakeChain, a large-scale benchmark comprising 1-, 2-, and 3-Step forgeries synthesized using five state-of-the-art representative generators. Using this approach, we analyze detection performance and spectral properties across hybrid manipulation at different step, along with varying generator combinations and quality settings. Surprisingly, our findings reveal that detection performance highly depends on the final manipulation type, with F1-score dropping by up to 58.83% when it differs from training distribution. This clearly demonstrates that detectors rely on last-stage artifacts rather than cumulative manipulation traces, limiting generalization. Such findings highlight the need for detection models to explicitly consider manipulation history and sequences. Our results highlight the importance of benchmarks such as FakeChain, reflecting growing synthesis complexity and diversity in real-world scenarios. Our sample code is available herefootnotehttps://github.com/minjihh/FakeChain.