# Attribution-Guided Multimodal Deepfake Detection via Cross-Modal Forensic Fingerprints

arXiv: https://arxiv.org/abs/2604.26453 · HTML: https://mlsanity.com/paper/2604.26453/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 41 references that are in the map.
- First posted on arXiv 29 Apr 2026.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (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)
- [A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild](https://mlsanity.com/paper/2008.10010/) (2020)
- [Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics](https://mlsanity.com/paper/1909.12962/) (2019)
- [How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)](https://mlsanity.com/paper/1703.07332/) (2017)
- [Leveraging Frequency Analysis for Deep Fake Image Recognition](https://mlsanity.com/paper/2003.08685/) (2020)
- [FSGAN: Subject Agnostic Face Swapping and Reenactment](https://mlsanity.com/paper/1908.05932/) (2019)
- [Exposing DeepFake Videos By Detecting Face Warping Artifacts](https://mlsanity.com/paper/1811.00656/) (2018)
- [Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis](https://mlsanity.com/paper/1806.04558/) (2018)
- [DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection](https://mlsanity.com/paper/2001.00179/) (2020)
- [FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset](https://mlsanity.com/paper/2108.05080/) (2021)
- [AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks](https://mlsanity.com/paper/2110.01200/) (2021)
- [Emotions Don't Lie: An Audio-Visual Deepfake Detection Method Using Affective Cues](https://mlsanity.com/paper/2003.06711/) (2020)
- [Detecting Deep-Fake Videos from Appearance and Behavior](https://mlsanity.com/paper/2004.14491/) (2020)
- [Half-Truth: A Partially Fake Audio Detection Dataset](https://mlsanity.com/paper/2104.03617/) (2021)
- [Self-supervised Transformer for Deepfake Detection](https://mlsanity.com/paper/2203.01265/) (2022)
- [Model Attribution of Face-swap Deepfake Videos](https://mlsanity.com/paper/2202.12951/) (2022)
- [Detecting Deepfake Videos Using Euler Video Magnification](https://mlsanity.com/paper/2101.11563/) (2021)
- [NPVForensics: Jointing Non-critical Phonemes and Visemes for Deepfake Detection](https://mlsanity.com/paper/2306.06885/) (2023)
- [CapST: Leveraging Capsule Networks and Temporal Attention for Accurate Model Attribution in Deep-fake Videos](https://mlsanity.com/paper/2311.03782/) (2023)
- [FAME: A Lightweight Spatio-Temporal Network for Model Attribution of Face-Swap Deepfakes](https://mlsanity.com/paper/2506.11477/) (2025)

## Abstract (arXiv)

Audio-visual deepfakes have reached a level of realism that makes perceptual detection unreliable, threatening media integrity and biometric security. While multimodal detection has shown promise, most approaches are binary classification tasks that often latch onto dataset-specific artifacts rather than genuine generative traces. We argue that a detector incapable of identifying how a video was forged is likely learning the wrong signal. Unlike binary detection, attribution-guided learning imposes a stronger geometric constraint on the shared embedding space, forcing the model to encode generator-specific forensic content rather than shortcuts. We propose the Attribution-Guided Multimodal Deepfake Detection (AMDD) framework, which jointly learns to detect and attribute manipulation. AMDD treats generator attribution as a structured regularization that constrains representation geometry toward forensically meaningful features. We introduce a Cross-Modal Forensic Fingerprint Consistency (CMFFC) loss to enforce alignment between generator-induced artifacts in visual and audio streams. This exploits the fact that coherent manipulation leaves correlated traces across modalities, grounded in the physical coupling between speech and facial articulation that synthetic pipelines routinely disrupt. Architecturally, we pair a ResNet50 with temporal attention for visual encoding against a pretrained ResNet18 for mel spectrograms, closing the encoder capacity gap found in prior models. On FakeAVCeleb, AMDD achieves 99.7% balanced accuracy and 99.8% AUC with 95.9% attribution accuracy. Cross-dataset evaluation on DeepfakeTIMIT, DFDM, and LAV-DF confirms that real video detection generalizes robustly, while fake detection on unseen generators remains an open challenge that we analyze in depth.