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

arXiv: https://arxiv.org/abs/2607.19476 · HTML: https://mlsanity.com/paper/2607.19476/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 39 references that are in the map.
- First posted on arXiv 21 Jul 2026.

## Builds on (most cited first, 30 of 31)

- [BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks](https://mlsanity.com/paper/1709.01686/) (2017)
- [Game-theoretic statistics and safe anytime-valid inference](https://mlsanity.com/paper/2210.01948/) (2022)
- [DeMamba: AI-Generated Video Detection on Million-Scale GenVideo Benchmark](https://mlsanity.com/paper/2405.19707/) (2024)
- [Hypothesis testing with e-values](https://mlsanity.com/paper/2410.23614/) (2024)
- [BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute](https://mlsanity.com/paper/2506.22716/) (2025)
- [When Does Confidence-Based Cascade Deferral Suffice?](https://mlsanity.com/paper/2307.02764/) (2023)
- [Ivy-Fake: A Unified Explainable Framework and Benchmark for Image and Video AIGC Detection](https://mlsanity.com/paper/2506.00979/) (2025)
- [AI-Generated Video Detection via Perceptual Straightening](https://mlsanity.com/paper/2507.00583/) (2025)
- [D3: Training-Free AI-Generated Video Detection Using Second-Order Features](https://mlsanity.com/paper/2508.00701/) (2025)
- [Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs](https://mlsanity.com/paper/2507.02076/) (2025)
- [GenVidBench: A 6-Million Benchmark for AI-Generated Video Detection](https://mlsanity.com/paper/2501.11340/) (2025)
- [Skyra: AI-Generated Video Detection via Grounded Artifact Reasoning](https://mlsanity.com/paper/2512.15693/) (2025)
- [Seeing What Matters: Generalizable AI-generated Video Detection with Forensic-Oriented Augmentation](https://mlsanity.com/paper/2506.16802/) (2025)
- [Window-Based Early-Exit Cascades for Uncertainty Estimation: When Deep Ensembles are More Efficient than Single Models](https://mlsanity.com/paper/2303.08010/) (2023)
- [VidGuard-R1: AI-Generated Video Detection and Explanation via Reasoning MLLMs and RL](https://mlsanity.com/paper/2510.02282/) (2025)
- [Your One-Stop Solution for AI-Generated Video Detection](https://mlsanity.com/paper/2601.11035/) (2026)
- [VideoVeritas: AI-Generated Video Detection via Perception Pretext Reinforcement Learning](https://mlsanity.com/paper/2602.08828/) (2026)
- [Preserving Forgery Artifacts: AI-Generated Video Detection at Native Scale](https://mlsanity.com/paper/2604.04634/) (2026)
- [CodecSight: Leveraging Video Codec Signals for Efficient Streaming VLM Inference](https://mlsanity.com/paper/2604.06036/) (2026)
- [Anytime Validity is Free: Inducing Sequential Tests](https://mlsanity.com/paper/2501.03982/) (2025)
- [See Without Decoding: Motion-Vector-Based Tracking in Compressed Video](https://mlsanity.com/paper/2602.00153/) (2026)
- [Artifact-Bench: Evaluating MLLMs on Detecting and Assessing the Artifacts of AI-Generated Videos](https://mlsanity.com/paper/2605.18984/) (2026)
- [Efficient Temporally-Aware DeepFake Detection using H.264 Motion Vectors](https://mlsanity.com/paper/2311.10788/) (2023)
- [A Spatial-Frequency Aware Multi-Scale Fusion Network for Real-Time Deepfake Detection](https://mlsanity.com/paper/2508.20449/) (2025)
- [CoCoVideo: The High-Quality Commercial-Model-Based Contrastive Benchmark for AI-Generated Video Detection](https://mlsanity.com/paper/2606.00101/) (2026)
- [Detection of Real-time DeepFakes in Video Conferencing with Active Probing and Corneal Reflection](https://mlsanity.com/paper/2210.14153/) (2022)
- [EdgeOAR: Real-time Online Action Recognition On Edge Devices](https://mlsanity.com/paper/2412.01267/) (2024)
- [GenVideoLens: Where LVLMs Fall Short in AI-Generated Video Detection?](https://mlsanity.com/paper/2603.18625/) (2026)
- [SpecSem-Net: Integrating Spectral and Semantic Features for Robust AI-generated Video Detection](https://mlsanity.com/paper/2605.17311/) (2026)
- [Auditing Generalization in AI-Generated Video Detection: A Six-Control Protocol and the VidAudit Toolkit](https://mlsanity.com/paper/2606.31004/) (2026)

## Abstract (arXiv)

Detectors for AI-generated video are evaluated offline. A clip is decoded to pixels and scored once, increasingly by a large vision-language model. Detection, however, is deployed online. We recast the task as streaming perception and score the motion field the codec already wrote into the bitstream. Reading that field is a parse, not a pixel-domain forward pass. Because the running aggregate is monotone, one end-calibrated threshold is anytime-valid at the data-dependent decision time. Recalibrating at each prefix is not. Escalation is priced in closed form. A compute budget maps to a deferral window, on a frontier monotone exactly where the deferral condition holds. On matched GenVidBench the codec stage reaches full-length AUC 0.64 at five orders of magnitude less compute than a pixel CNN, on CPU. Its gate holds the stopping-time false-positive rate at target while the real data match its calibration, and drifts above it under distribution shift. Deferring 15% of clips lifts accuracy from 0.75 to 0.78 at 7× less compute (paired: McNemar p<10-6). The stage-1 ordering replicates on AIGVDBench. We introduce no new detector. The contribution is the reframing, two guarantees, and the measured frontiers. Code, configurations, and evaluation splits: https://github.com/KurbanIntelligenceLab/streamdet.