D3: Training-Free AI-Generated Video Detection Using Second-Order Features
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911091419774976 |
|---|---|
| author | Zheng, Chende suo, Ruiqi Lin, Chenhao Zhao, Zhengyu Yang, Le Liu, Shuai Yang, Minghui Wang, Cong Shen, Chao |
| author_facet | Zheng, Chende suo, Ruiqi Lin, Chenhao Zhao, Zhengyu Yang, Le Liu, Shuai Yang, Minghui Wang, Cong Shen, Chao |
| contents | The evolution of video generation techniques, such as Sora, has made it increasingly easy to produce high-fidelity AI-generated videos, raising public concern over the dissemination of synthetic content. However, existing detection methodologies remain limited by their insufficient exploration of temporal artifacts in synthetic videos. To bridge this gap, we establish a theoretical framework through second-order dynamical analysis under Newtonian mechanics, subsequently extending the Second-order Central Difference features tailored for temporal artifact detection. Building on this theoretical foundation, we reveal a fundamental divergence in second-order feature distributions between real and AI-generated videos. Concretely, we propose Detection by Difference of Differences (D3), a novel training-free detection method that leverages the above second-order temporal discrepancies. We validate the superiority of our D3 on 4 open-source datasets (Gen-Video, VideoPhy, EvalCrafter, VidProM), 40 subsets in total. For example, on GenVideo, D3 outperforms the previous best method by 10.39% (absolute) mean Average Precision. Additional experiments on time cost and post-processing operations demonstrate D3's exceptional computational efficiency and strong robust performance. Our code is available at https://github.com/Zig-HS/D3. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_00701 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | D3: Training-Free AI-Generated Video Detection Using Second-Order Features Zheng, Chende suo, Ruiqi Lin, Chenhao Zhao, Zhengyu Yang, Le Liu, Shuai Yang, Minghui Wang, Cong Shen, Chao Computer Vision and Pattern Recognition Artificial Intelligence The evolution of video generation techniques, such as Sora, has made it increasingly easy to produce high-fidelity AI-generated videos, raising public concern over the dissemination of synthetic content. However, existing detection methodologies remain limited by their insufficient exploration of temporal artifacts in synthetic videos. To bridge this gap, we establish a theoretical framework through second-order dynamical analysis under Newtonian mechanics, subsequently extending the Second-order Central Difference features tailored for temporal artifact detection. Building on this theoretical foundation, we reveal a fundamental divergence in second-order feature distributions between real and AI-generated videos. Concretely, we propose Detection by Difference of Differences (D3), a novel training-free detection method that leverages the above second-order temporal discrepancies. We validate the superiority of our D3 on 4 open-source datasets (Gen-Video, VideoPhy, EvalCrafter, VidProM), 40 subsets in total. For example, on GenVideo, D3 outperforms the previous best method by 10.39% (absolute) mean Average Precision. Additional experiments on time cost and post-processing operations demonstrate D3's exceptional computational efficiency and strong robust performance. Our code is available at https://github.com/Zig-HS/D3. |
| title | D3: Training-Free AI-Generated Video Detection Using Second-Order Features |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2508.00701 |