Detecting AI-Generated Video via Frame Consistency

TL;DR

This paper introduces a new open-source dataset and a novel frame consistency-based detection method, DeCoF, to identify AI-generated videos, emphasizing temporal artifacts for improved generalizability.

Contribution

The paper presents the first open-source dataset for generated video detection and proposes DeCoF, a temporal artifact-focused detection model that outperforms spatial artifact-based methods.

Findings

DeCoF effectively detects videos from unseen generation models.

DeCoF demonstrates strong generalizability across proprietary models.

The dataset covers diverse forgery scenarios and generation techniques.

Abstract

The escalating quality of video generated by advanced video generation methods results in new security challenges, while there have been few relevant research efforts: 1) There is no open-source dataset for generated video detection, 2) No generated video detection method has been proposed so far. To this end, we propose an open-source dataset and a detection method for generated video for the first time. First, we propose a scalable dataset consisting of 964 prompts, covering various forgery targets, scenes, behaviors, and actions, as well as various generation models with different architectures and generation methods, including the most popular commercial models like OpenAI's Sora and Google's Veo. Second, we found via probing experiments that spatial artifact-based detectors lack generalizability. Hence, we propose a simple yet effective \textbf{de}tection model based on \textbf{f}rame \textbf{co}nsistency (\textbf{DeCoF}), which focuses on temporal artifacts by eliminating the impact of spatial artifacts during feature learning. Extensive experiments demonstrate the efficacy of DeCoF in detecting videos generated by unseen video generation models and confirm its powerful generalizability across several commercially proprietary models.