# Turns Out I'm Not Real: Towards Robust Detection of AI-Generated Videos

arXiv: https://arxiv.org/abs/2406.09601 · HTML: https://mlsanity.com/paper/2406.09601/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 14 of its 20 references that are in the map.
- First posted on arXiv 13 Jun 2024.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 14 of 14)

- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- [DIRE for Diffusion-Generated Image Detection](https://mlsanity.com/paper/2303.09295/) (2023)
- [Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation](https://mlsanity.com/paper/2309.15818/) (2023)
- [On the detection of synthetic images generated by diffusion models](https://mlsanity.com/paper/2211.00680/) (2022)
- [DeepFakes: a New Threat to Face Recognition? Assessment and Detection](https://mlsanity.com/paper/1812.08685/) (2018)
- [Towards the Detection of Diffusion Model Deepfakes](https://mlsanity.com/paper/2210.14571/) (2022)
- [Exposing the Fake: Effective Diffusion-Generated Images Detection](https://mlsanity.com/paper/2307.06272/) (2023)
- [Detecting Images Generated by Deep Diffusion Models using their Local Intrinsic Dimensionality](https://mlsanity.com/paper/2307.02347/) (2023)
- [DETER: Detecting Edited Regions for Deterring Generative Manipulations](https://mlsanity.com/paper/2312.10539/) (2023)

## Built on by (most cited first, 21 of 21)

- [D3: Training-Free AI-Generated Video Detection Using Second-Order Features](https://mlsanity.com/paper/2508.00701/) (2025)
- [Seeing What Matters: Generalizable AI-generated Video Detection with Forensic-Oriented Augmentation](https://mlsanity.com/paper/2506.16802/) (2025)
- [VidGuard-R1: AI-Generated Video Detection and Explanation via Reasoning MLLMs and RL](https://mlsanity.com/paper/2510.02282/) (2025)
- [Survey on AI-Generated Media Detection: From Non-MLLM to MLLM](https://mlsanity.com/paper/2502.05240/) (2025)
- [VideoVeritas: AI-Generated Video Detection via Perception Pretext Reinforcement Learning](https://mlsanity.com/paper/2602.08828/) (2026)
- [DAVID-XR1: Detecting AI-Generated Videos with Explainable Reasoning](https://mlsanity.com/paper/2506.14827/) (2025)
- [REVEAL: Robust Evolution of Vision-Language Models for Explainable AI-Video Detection](https://mlsanity.com/paper/2502.14994/) (2025)
- [BrokenVideos: A Benchmark Dataset for Fine-Grained Artifact Localization in AI-Generated Videos](https://mlsanity.com/paper/2506.20103/) (2025)
- [RobustSora: De-Watermarked Benchmark for Robust AI-Generated Video Detection](https://mlsanity.com/paper/2512.10248/) (2025)
- [CMTA: Leveraging Cross-Modal Temporal Artifacts for Generalizable AI-Generated Video Detection](https://mlsanity.com/paper/2605.00630/) (2026)
- [Rethinking the Readout: Unlocking Video Backbones for AI-Generated Video Detection](https://mlsanity.com/paper/2607.15321/) (2026)
- [Video Forgery Detection with Optical Flow Residuals and Spatial-Temporal Consistency](https://mlsanity.com/paper/2508.00397/) (2025)
- [GenVideoLens: Where LVLMs Fall Short in AI-Generated Video Detection?](https://mlsanity.com/paper/2603.18625/) (2026)
- [Leave No Stone Unturned: Uncovering Holistic Audio-Visual Intrinsic Coherence for Deepfake Detection](https://mlsanity.com/paper/2603.23960/) (2026)
- [ATSS: Detecting AI-Generated Videos via Anomalous Temporal Self-Similarity](https://mlsanity.com/paper/2604.04029/) (2026)
- [SpecSem-Net: Integrating Spectral and Semantic Features for Robust AI-generated Video Detection](https://mlsanity.com/paper/2605.17311/) (2026)
- [Dataset Biases and Shortcut Learning in Motion-Based AI-Generated Video Detection](https://mlsanity.com/paper/2607.00948/) (2026)
- [Detecting AI-Generated Video: A Vision-Language Dual-View Survey](https://mlsanity.com/paper/2607.10787/) (2026)
- [DBINDS -- Can Initial Noise from Diffusion Model Inversion Help Reveal AI-Generated Videos?](https://mlsanity.com/paper/2511.09184/) (2025)
- [Scalable, Energy-Efficient Optical-Neural Architecture for Multiplexed Deepfake Video Detection](https://mlsanity.com/paper/2605.19360/) (2026)
- [TRACE: Trajectory Representation and Consistency Estimation for AI-Generated Video Detection](https://mlsanity.com/paper/2609.25775/) (2026)

## Abstract (arXiv)

The impressive achievements of generative models in creating high-quality videos have raised concerns about digital integrity and privacy vulnerabilities. Recent works to combat Deepfakes videos have developed detectors that are highly accurate at identifying GAN-generated samples. However, the robustness of these detectors on diffusion-generated videos generated from video creation tools (e.g., SORA by OpenAI, Runway Gen-2, and Pika, etc.) is still unexplored. In this paper, we propose a novel framework for detecting videos synthesized from multiple state-of-the-art (SOTA) generative models, such as Stable Video Diffusion. We find that the SOTA methods for detecting diffusion-generated images lack robustness in identifying diffusion-generated videos. Our analysis reveals that the effectiveness of these detectors diminishes when applied to out-of-domain videos, primarily because they struggle to track the temporal features and dynamic variations between frames. To address the above-mentioned challenge, we collect a new benchmark video dataset for diffusion-generated videos using SOTA video creation tools. We extract representation within explicit knowledge from the diffusion model for video frames and train our detector with a CNN + LSTM architecture. The evaluation shows that our framework can well capture the temporal features between frames, achieves 93.7% detection accuracy for in-domain videos, and improves the accuracy of out-domain videos by up to 16 points.