Benchmark RadarAI BENCHMARK PROFILE
SynCred-Bench
SynCred-Bench evaluates detection of AI-generated visual misinformation with synthetic credibility, using 600 AI-generated images and FP450 real-image negatives.
- Released
- 2026-06-02
- Readiness
- Paper only
- Primary field
- General AI
Why it matters
No public artifacts or reuse path are provided, and the benchmark lacks a clear scoring contract for independent runs.
Motivation
Recent generative models can now produce visual artifacts with realistic embedded text and layouts, creating a new misinformation threat: synthetic credibility.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.