# Seeing What Matters: Generalizable AI-generated Video Detection with Forensic-Oriented Augmentation

arXiv: https://arxiv.org/abs/2506.16802 · HTML: https://mlsanity.com/paper/2506.16802/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 69 of its 96 references that are in the map.
- First posted on arXiv 20 Jun 2025.

## Builds on (most cited first, 30 of 69)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- [WorldSimBench: Towards Video Generation Models as World Simulators](https://mlsanity.com/paper/2410.18072/) (2024)
- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (2023)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators](https://mlsanity.com/paper/2303.13439/) (2023)
- [ModelScope Text-to-Video Technical Report](https://mlsanity.com/paper/2308.06571/) (2023)
- [Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation](https://mlsanity.com/paper/2310.05737/) (2023)
- [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)
- [Towards Universal Fake Image Detectors that Generalize Across Generative Models](https://mlsanity.com/paper/2302.10174/) (2023)
- [Face X-ray for More General Face Forgery Detection](https://mlsanity.com/paper/1912.13458/) (2019)
- [Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers](https://mlsanity.com/paper/2402.19479/) (2024)
- [DIRE for Diffusion-Generated Image Detection](https://mlsanity.com/paper/2303.09295/) (2023)
- [Pyramidal Flow Matching for Efficient Video Generative Modeling](https://mlsanity.com/paper/2410.05954/) (2024)
- [Multi-attentional Deepfake Detection](https://mlsanity.com/paper/2103.02406/) (2021)
- [Open-Sora Plan: Open-Source Large Video Generation Model](https://mlsanity.com/paper/2412.00131/) (2024)
- [Detecting and Simulating Artifacts in GAN Fake Images](https://mlsanity.com/paper/1907.06515/) (2019)
- [Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles](https://mlsanity.com/paper/2306.00989/) (2023)
- [Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detection](https://mlsanity.com/paper/2012.07657/) (2020)
- [On the detection of synthetic images generated by diffusion models](https://mlsanity.com/paper/2211.00680/) (2022)
- [Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral Distributions](https://mlsanity.com/paper/2003.01826/) (2020)
- [Global Texture Enhancement for Fake Face Detection in the Wild](https://mlsanity.com/paper/2002.00133/) (2020)

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

- [Your One-Stop Solution for AI-Generated Video Detection](https://mlsanity.com/paper/2601.11035/) (2026)
- [DyaPlex: Full-Duplex Speech-Motion Model for Dyadic Interaction](https://mlsanity.com/paper/2606.03874/) (2026)
- [MPF-Net: Exposing High-Fidelity AI-Generated Video Forgeries via Hierarchical Manifold Deviation and Micro-Temporal Fluctuations](https://mlsanity.com/paper/2601.21408/) (2026)
- [SafeGuard: A Multi-Agent Perception-Reasoning Framework for Social-Risk AI-Generated Video Detection](https://mlsanity.com/paper/2607.03069/) (2026)
- [GenVideoLens: Where LVLMs Fall Short in AI-Generated Video Detection?](https://mlsanity.com/paper/2603.18625/) (2026)
- [Video as Natural Augmentation: Towards Unified AI-Generated Image and Video Detection](https://mlsanity.com/paper/2605.21977/) (2026)
- [HydraPrompt: An Adaptive and Asymmetric Framework of Vision-Language Models for Synthetic Image Detection](https://mlsanity.com/paper/2605.26421/) (2026)
- [Revealing Artifacts via Noise Amplification: A Novel Perspective for AI-Generated Video Detection](https://mlsanity.com/paper/2606.16742/) (2026)
- [Auditing Generalization in AI-Generated Video Detection: A Six-Control Protocol and the VidAudit Toolkit](https://mlsanity.com/paper/2606.31004/) (2026)
- [Dataset Biases and Shortcut Learning in Motion-Based AI-Generated Video Detection](https://mlsanity.com/paper/2607.00948/) (2026)
- [VidForensics-M1: Meta-Detection Reinforcement Learning with Verifiable Temporal Grounding for AI-Generated Video Forensics](https://mlsanity.com/paper/2608.11201/) (2026)
- [DinoLizer: Separating VAE and Diffusion Artifacts in Generative Inpainting Localization](https://mlsanity.com/paper/2511.20722/) (2025)
- [EA-Swin: An Embedding-Agnostic Swin Transformer for AI-Generated Video Detection](https://mlsanity.com/paper/2602.17260/) (2026)
- [Advancing Reliable Synthetic Video Detection: Insights from the SAFE Challenge](https://mlsanity.com/paper/2605.06912/) (2026)
- [Backbone is All You Need: Assessing Vulnerabilities of Frozen Foundation Models in Synthetic Image Forensics](https://mlsanity.com/paper/2605.13381/) (2026)
- [G2VD: Generalizable AI-Generated Video Detection via Counterfactual Intervention and Causal Disentanglement](https://mlsanity.com/paper/2607.04607/) (2026)
- [Detect Early, Escalate Rarely: Anytime Detection of AI-Generated Video from the Compressed Bitstream](https://mlsanity.com/paper/2607.19476/) (2026)
- [V-FIND: Revealing the Intrinsic Forgery Knowledge Encoded in Video Forgery Detectors](https://mlsanity.com/paper/2608.03008/) (2026)
- [Understanding Why Foundation Models Work for Diffusion-Generated Image Detection](https://mlsanity.com/paper/2608.12155/) (2026)
- [MotionPhys: Detecting AI-Generated Videos via Physical Consistency of Optical-Flow Trajectories](https://mlsanity.com/paper/2608.20770/) (2026)
- [TUE-Detector: A Tool-Using Expert MLLM-Based Detector for AI-Generated Videos](https://mlsanity.com/paper/2608.30704/) (2026)
- [TRACE: Trajectory Representation and Consistency Estimation for AI-Generated Video Detection](https://mlsanity.com/paper/2609.25775/) (2026)
- [IVT-Guard: All-in-One Reasoning Model for AI-Generated Content Detection](https://mlsanity.com/paper/2609.33585/) (2026)

## Abstract (arXiv)

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.