# Semantic Watermark Detection on CelebA-HQ protected DreamBooth-generated Source: [Semantic Watermark Detection on CelebA-HQ protected DreamBooth-generated]() Collection index: [llms.txt]() Data updated: 2026-06-11T06:55:00.020Z Evaluation of the ability to detect semantic watermarks embedded within images generated using the DreamBooth technique applied to the CelebA-HQ dataset. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Semantic Watermark Detection | | Dataset (including any stated split) | CelebA-HQ protected DreamBooth-generated | | Metric | Detection Percentage | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 1 of 1 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Detection Percentage](): Higher is better; unit: PERCENT. ## Recorded results | Method | Detection Percentage | Result date | Report paper | | --- | --- | --- | --- | | DIAGNOSIS | 17.24 | Not recorded | 6a28f33f90966ade919c1717 | ### DIAGNOSIS Detection Percentage: 17.24. Result ID: 6a2a5b02fbc373592c26dd07. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"DreamBooth","Fine-tuning images":"5 per group","Protection":"DIAGNOSIS"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.