ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910001406148608 |
|---|---|
| author | Du, Bo Zhu, Xuekang Ma, Xiaochen Qu, Chenfan Feng, Kaiwen Yang, Zhe Pun, Chi-Man Liu, Jian Zhou, Ji-Zhe |
| author_facet | Du, Bo Zhu, Xuekang Ma, Xiaochen Qu, Chenfan Feng, Kaiwen Yang, Zhe Pun, Chi-Man Liu, Jian Zhou, Ji-Zhe |
| contents | The field of Fake Image Detection and Localization (FIDL) is highly fragmented, encompassing four domains: deepfake detection (Deepfake), image manipulation detection and localization (IMDL), artificial intelligence-generated image detection (AIGC), and document image manipulation localization (Doc). Although individual benchmarks exist in some domains, a unified benchmark for all domains in FIDL remains blank. The absence of a unified benchmark results in significant domain silos, where each domain independently constructs its datasets, models, and evaluation protocols without interoperability, preventing cross-domain comparisons and hindering the development of the entire FIDL field. To close the domain silo barrier, we propose ForensicHub, the first unified benchmark & codebase for all-domain fake image detection and localization. Considering drastic variations on dataset, model, and evaluation configurations across all domains, as well as the scarcity of open-sourced baseline models and the lack of individual benchmarks in some domains, ForensicHub: i) proposes a modular and configuration-driven architecture that decomposes forensic pipelines into interchangeable components across datasets, transforms, models, and evaluators, allowing flexible composition across all domains; ii) fully implements 10 baseline models, 6 backbones, 2 new benchmarks for AIGC and Doc, and integrates 2 existing benchmarks of DeepfakeBench and IMDLBenCo through an adapter-based design; iii) conducts indepth analysis based on the ForensicHub, offering 8 key actionable insights into FIDL model architecture, dataset characteristics, and evaluation standards. ForensicHub represents a significant leap forward in breaking the domain silos in the FIDL field and inspiring future breakthroughs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_11003 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localization Du, Bo Zhu, Xuekang Ma, Xiaochen Qu, Chenfan Feng, Kaiwen Yang, Zhe Pun, Chi-Man Liu, Jian Zhou, Ji-Zhe Computer Vision and Pattern Recognition The field of Fake Image Detection and Localization (FIDL) is highly fragmented, encompassing four domains: deepfake detection (Deepfake), image manipulation detection and localization (IMDL), artificial intelligence-generated image detection (AIGC), and document image manipulation localization (Doc). Although individual benchmarks exist in some domains, a unified benchmark for all domains in FIDL remains blank. The absence of a unified benchmark results in significant domain silos, where each domain independently constructs its datasets, models, and evaluation protocols without interoperability, preventing cross-domain comparisons and hindering the development of the entire FIDL field. To close the domain silo barrier, we propose ForensicHub, the first unified benchmark & codebase for all-domain fake image detection and localization. Considering drastic variations on dataset, model, and evaluation configurations across all domains, as well as the scarcity of open-sourced baseline models and the lack of individual benchmarks in some domains, ForensicHub: i) proposes a modular and configuration-driven architecture that decomposes forensic pipelines into interchangeable components across datasets, transforms, models, and evaluators, allowing flexible composition across all domains; ii) fully implements 10 baseline models, 6 backbones, 2 new benchmarks for AIGC and Doc, and integrates 2 existing benchmarks of DeepfakeBench and IMDLBenCo through an adapter-based design; iii) conducts indepth analysis based on the ForensicHub, offering 8 key actionable insights into FIDL model architecture, dataset characteristics, and evaluation standards. ForensicHub represents a significant leap forward in breaking the domain silos in the FIDL field and inspiring future breakthroughs. |
| title | ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.11003 |