@unpublished{robust:gmcv24,
    author = "Liu, Qingyuan and Shi, Pengyuan and Tsai, Yun-Yun and Mao, Chengzhi and Yang, Junfeng",
    abstract = "The impressive achievements of generative models in creating high-quality videos have raised concerns about digital integrity and privacy vulnerabilities. Recent works to combat Deepfakes videos have developed detectors that are highly accurate at identifying GAN-generated samples. However, the robustness of these detectors on diffusion-generated videos generated from video creation tools (e.g., SORA by OpenAI, Runway Gen-2, and Pika, etc.) is still unexplored. In this paper, we propose a novel framework for detecting videos synthesized from multiple state-of-the-art (SOTA) generative models, such as Stable Video Diffusion. We find that the SOTA methods for detecting diffusion-generated images lack robustness in identifying diffusion-generated videos. Our analysis reveals that the effectiveness of these detectors diminishes when applied to out-of-domain videos, primarily because they struggle to track the temporal features and dynamic variations between frames. To address the above-mentioned challenge, we collect a new benchmark video dataset for diffusion-generated videos using SOTA video creation tools. We extract representation within explicit knowledge from the diffusion model for video frames and train our detector with a CNN + LSTM architecture. The evaluation shows that our framework can well capture the temporal features between frames, achieves 93.7\% detection accuracy for in-domain videos, and improves the accuracy of out-domain videos by up to 16 points.",
    title = "Turns Out I'm Not Real: Towards Robust Detection of AI-Generated Videos",
    booktitle = "2nd Workshop on Generative Models for Computer Vision (GCV), held with CVPR",
    note = "2nd Workshop on Generative Models for Computer Vision (GCV), held with CVPR; non-archival workshop paper",
    eprint = "2406.09601",
    archivePrefix = "arXiv",
    primaryClass = "cs.CV",
    url = "https://arxiv.org/abs/2406.09601",
    pdfurl = "https://arxiv.org/pdf/2406.09601",
    month = "June",
    year = "2024"
}