cs.CVNov 16, 2026

VAE Rhythm: Temporal Decoding Traces for AI-Generated Video Detection

Authors: Ke Sun, Shuwei Li, Haiyang Mei, Mike Zheng Shou

Organizations: Show Lab, National University of Singapore

Abstract

Visible artifacts are an unreliable cue for detecting generated videos, because newer generators learn to remove them. We instead detect a trace left by the generation pipeline itself. Most video generators decode latents with a 3D causal VAE that groups consecutive frames in time, so the fidelity of generated frames rises and falls periodically with their position in a group. We call this periodic trace VAE Rhythm. Real videos are captured frame by frame and do not have it. To reveal it without training, we propose a phase scan. The scan reconstructs a clip with an off-the-shelf VAE from successive start offsets and measures the periodicity of the reconstruction error across these offsets. We find VAE Rhythm in most of the 39 variants of 31 generators we test, including the closed-source Sora, Kling 3.0 and Seedance 2.0. We use the rhythm as a zero-shot score, as a plug-in for existing detectors and as a data engine that pairs real videos with their VAE reconstructions to train our detector CaDet. On DF26, the training-free rhythm score outperforms all 15 retrained baselines, and as a plug-in it improves all 19 tested detectors by 6.7% to 23.7% AUROC. CaDet achieves the best AUROC on AIGVDBench, DF26 and three 2026 closed-source models, and its variant trained without any generated video still exceeds 90% on AIGVDBench.

Figures & tables

Explore similar work

CardsList
  1. TRACE: Trajectory Representation and Consistency Estimation for AI-Generated Video Detection

    Sep 22, 2026Huangsen Cao, Hongkang chu, Siyao Yu +3Deepfake DetectionVideo Forensics

  2. Detect Early, Escalate Rarely: Anytime Detection of AI-Generated Video from the Compressed Bitstream

    Jul 21, 2026Mert Onur Cakiroglu, Mehmet Dalkilic, Hasan KurbanDeepfake DetectionSequential Hypothesis Testing

  3. Temporal Slice Learning for AI-Generated Video Detection with 400×\times Fewer FLOPs

    Oct 26, 2026Wei Shang, Zhiyuan Li, Shengfeng HeFrequency-Domain AnalysisDeepfake Detection