ForensicHub: AUnified Benchmark & Codebase for All-Domain Fake Image Detection and Localization
–Neural Information Processing Systems
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.
Neural Information Processing Systems
Jun-17-2026, 14:58:36 GMT
- Country:
- Asia > China (0.28)
- North America
- United States (0.46)
- Canada (0.28)
- Genre:
- Research Report > New Finding (0.92)
- Industry:
- Information Technology > Security & Privacy (1.00)
- Technology: