Deepfake vs Real Portrait Images for Binary Classification, 28,000 Samples

Deepfake-vs-Real-1440px-Max is a curated dataset of 28,000 portrait images for binary classification tasks. It was created by prithivMLmods and last updated on April 28, 2025. The dataset is intended for training and evaluating models in deepfake detection and media authenticity analysis.

Use Cases

• Train binary image classifiers to distinguish deepfake portraits from real portraits based on the described classification task.
• Evaluate model performance in media authenticity analysis using the provided portrait images.
• Benchmark facial integrity recognition algorithms on a dedicated dataset of fake and real faces.

Strengths

• Contains 28,000 images, providing a substantial sample size for model training.
• Specifically curated for a binary classification task, offering clear labeling for deepfake vs. real portraits.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Description metadata is limited; actual data quality, image resolution, and source details require manual inspection.

Provenance

Source

prithivMLmods on Hugging Face

Collection Method

Curated dataset; specific collection method is not described.

Time Range

null

Freshness

Last updated 2025-04 28 03:52:37; freshness should be verified.

Geography

null