cs.CVNov 11, 2026

Reality Perception Gap: Are AI-Manipulated Video Detectors Ready for the Real World?

Authors: Xiangrui Liu, Xinmiao Luan, Xinyuan Wang, Zhiyuan Fang, Chi-Yao Huang, Douglas C. Montgomery, Yanjie Fu, Felix Juefei-Xu, 

Organizations: Arizona State University · New York University

Abstract

AI-manipulated video detectors are typically evaluated on clean, curated datasets. In deployment, however, videos have usually passed through repost compression on social-media platforms and sometimes were captured by imperfect hardware. To measure detection under these conditions, we introduce Reality Perception Gap (RPG), a benchmark of 10,000 videos from frontier generators and partially synthetic edits, processed with cross-platform repost compression and paired with real footage that carries camera-side optical artifacts. RPG also includes socially fragile content, such as crime and wartime footage, where fabricated videos can cause severe social harm. Across 18 detectors, none catches more than 15% of fakes at a 1% false-positive rate. A positive control and a re-encoding sweep separate two sources of failure: generator and content shift degrades detectors before any compression, and repost compression erases the low-level traces that the artifact-based detectors relies on. Existing detectors therefore struggle when deployment conditions strip away the generation artifacts they rely on. These complementary failures suggest that robust detection requires training under deployment conditions and combining low-level, temporal, and semantic evidence, where passive detection may have reached its limits.

Figures & tables

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Can We Defend Against AI-Generated Video Attacks on Real-World Crisis Events? A Systematic Evaluation of Detectors, Generators and Social Dissemination

    Aug 14, 2026Shuo Liang, Yixing Ma, Pengfei Zhou +33Deepfake DetectionSynthetic Video Detection Benchmarks

  2. DF26: We Cannot Tell Fake From Real Anymore

    Sep 7, 2026Severyn Shykula, Andrii Yermakov, Ivan Samarskyi +3T2V GenerationOOD Generalization

  3. SPLIT: Training-Free AI-Generated and Partially Edited Video Detection via Spatial Patch-Level Incoherence and Temporal Roughness

    Jul 3, 2026Jongyeop Hyun, Hyounghun KimDeepfake Detection