1. [Publications](/index.php/publications)
2. Seeing What Matters: Generalizable AI-generated Video Detection with Forensic-Oriented Augmentation
 
 # Seeing What Matters: Generalizable AI-generated Video Detection with Forensic-Oriented Augmentation

  ![](/sites/default/files/styles/wide/public/publications/Untitled%202_0.png?itok=ZdkQseAk)

 Synthetic video generation is progressing very rapidly. The latest models can produce very realistic high-resolution videos that are virtually indistinguishable from real ones. Although several video forensic detectors have been recently proposed, they often exhibit poor generalization, which limits their applicability in a real-world scenario. Our key insight to overcome this issue is to guide the detector towards *seeing what really matters*. In fact, a well-designed forensic classifier should focus on identifying intrinsic low-level artifacts introduced by a generative architecture rather than relying on high-level semantic flaws that characterize a specific model. In this work, first, we study different generative architectures, searching and identifying discriminative features that are unbiased, robust to impairments, and shared across models. Then, we introduce a novel forensic-oriented data augmentation strategy based on the wavelet decomposition and replace specific frequency-related bands to drive the model to exploit more relevant forensic cues. Our novel training paradigm improves the generalizability of AI-generated video detectors, without the need for complex algorithms and large datasets that include multiple synthetic generators. To evaluate our approach, we train the detector using data from a single generative model and test it against videos produced by a wide range of other models. Despite its simplicity, our method achieves a significant accuracy improvement over state-of-the-art detectors and obtains excellent results even on very recent generative models, such as NOVA and FLUX.



 ## Authors



Riccardo Corvi (University Federico II of Naple)

Davide Cozzolino (University Federico II of Naple)

[Ekta Prashnani](/index.php/person/ekta-prashnani)

[Shalini De Mello](/index.php/person/shalini-de-mello)

[Koki Nagano](/index.php/person/koki-nagano)

Luisa Verdoliva (University Federico II of Naple)

 

 

 ## Publication Date



Sunday, November 30, 2025

 

 ## Published in



[Advances in Neural Information Processing Systems (NeurIPS) 2025](https://neurips.cc/virtual/2025/loc/san-diego/poster/117010)

 

 ## Research Area



[Artificial Intelligence and Machine Learning ](/index.php/research-area/machine-learning-artificial-intelligence)

[Computer Vision](/index.php/research-area/computer-vision)

[Generative AI](/index.php/research-area/generative-ai)

 

 

 ## External Links



[Code](https://github.com/grip-unina/WaveRep-SyntheticVideoDetection/)

[Project Page](https://grip-unina.github.io/WaveRep-SyntheticVideoDetection/)

[ArXiv](https://arxiv.org/abs/2506.16802)

 

 

 ## Uploaded Files



[Paper](https://d1qx31qr3h6wln.cloudfront.net/publications/SyntheticVideosDetection%20%283%29.pdf "Open file in new window")28.2 MB