Training-free Detection of Generated Videos via Spatial-Temporal Likelihoods
This addresses the critical need for reliable detection of AI-generated videos to prevent misinformation, offering a model-agnostic solution that generalizes to unseen generators, though it is incremental as it builds on zero-shot approaches.
The paper tackles the problem of detecting synthetic videos to combat misinformation by introducing STALL, a training-free detector that models spatial-temporal likelihoods, achieving consistent outperformance over prior baselines on public benchmarks and a new benchmark with state-of-the-art models.
Following major advances in text and image generation, the video domain has surged, producing highly realistic and controllable sequences. Along with this progress, these models also raise serious concerns about misinformation, making reliable detection of synthetic videos increasingly crucial. Image-based detectors are fundamentally limited because they operate per frame and ignore temporal dynamics, while supervised video detectors generalize poorly to unseen generators, a critical drawback given the rapid emergence of new models. These challenges motivate zero-shot approaches, which avoid synthetic data and instead score content against real-data statistics, enabling training-free, model-agnostic detection. We introduce \emph{STALL}, a simple, training-free, theoretically justified detector that provides likelihood-based scoring for videos, jointly modeling spatial and temporal evidence within a probabilistic framework. We evaluate STALL on two public benchmarks and introduce ComGenVid, a new benchmark with state-of-the-art generative models. STALL consistently outperforms prior image- and video-based baselines. Code and data are available at https://omerbenhayun.github.io/stall-video.