LAVID: An Agentic LVLM Framework for Diffusion-Generated Video Detection
This addresses digital integrity and privacy concerns by providing a more transparent and adaptable detection method for AI-generated videos, though it is incremental as it builds on existing LVLM capabilities.
The paper tackles the problem of detecting AI-generated videos, which is underexplored compared to images, by proposing LAVID, a training-free framework using Large Vision Language Models (LVLMs) with explicit knowledge enhancement and adaptive prompts. It achieves improvements in F1 scores by 6.2 to 30.2% over top baselines on a new benchmark dataset.
The impressive achievements of generative models in creating high-quality videos have raised concerns about digital integrity and privacy vulnerabilities. Recent works of AI-generated content detection have been widely studied in the image field (e.g., deepfake), yet the video field has been unexplored. Large Vision Language Model (LVLM) has become an emerging tool for AI-generated content detection for its strong reasoning and multimodal capabilities. It breaks the limitations of traditional deep learning based methods faced with like lack of transparency and inability to recognize new artifacts. Motivated by this, we propose LAVID, a novel LVLMs-based ai-generated video detection with explicit knowledge enhancement. Our insight list as follows: (1) The leading LVLMs can call external tools to extract useful information to facilitate its own video detection task; (2) Structuring the prompt can affect LVLM's reasoning ability to interpret information in video content. Our proposed pipeline automatically selects a set of explicit knowledge tools for detection, and then adaptively adjusts the structure prompt by self-rewriting. Different from prior SOTA that trains additional detectors, our method is fully training-free and only requires inference of the LVLM for detection. To facilitate our research, we also create a new benchmark \vidfor with high-quality videos generated from multiple sources of video generation tools. Evaluation results show that LAVID improves F1 scores by 6.2 to 30.2% over the top baselines on our datasets across four SOTA LVLMs.