FakeI2V-Bench

What is FakeI2V-Bench?

FakeI2V-Bench is a benchmark for evaluating image-level and video-level deepfake detectors in video detection scenarios. It comprises 97,548 videos generated…

Released

2026-08-04

Evaluates

General AI, Vision & 3D, cs.CR

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2608.03096

FakeI2V-Bench paper and code

• Paper https://arxiv.org/abs/2608.03096
• Code https://github.com/CryptoAILab/FakeI2V-Bench

Which sources cite FakeI2V-Bench?

• FakeI2V-Bench

Related General AI, Vision & 3D, cs.CR benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A3S-Bench
• AARRI-Bench
• ActBench
• ActiveSciBench
• ActiveVision