{"ID":2877010,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.20449","arxiv_id":"2508.20449","title":"A Spatial-Frequency Aware Multi-Scale Fusion Network for Real-Time Deepfake Detection","abstract":"With the rapid advancement of real-time deepfake generation techniques, forged content is becoming increasingly realistic and widespread across applications like video conferencing and social media. Although state-of-the-art detectors achieve high accuracy on standard benchmarks, their heavy computational cost hinders real-time deployment in practical applications. To address this, we propose the Spatial-Frequency Aware Multi-Scale Fusion Network (SFMFNet), a lightweight yet effective architecture for real-time deepfake detection. We design a spatial-frequency hybrid aware module that jointly leverages spatial textures and frequency artifacts through a gated mechanism, enhancing sensitivity to subtle manipulations. A token-selective cross attention mechanism enables efficient multi-level feature interaction, while a residual-enhanced blur pooling structure helps retain key semantic cues during downsampling. Experiments on several benchmark datasets show that SFMFNet achieves a favorable balance between accuracy and efficiency, with strong generalization and practical value for real-time applications.","short_abstract":"With the rapid advancement of real-time deepfake generation techniques, forged content is becoming increasingly realistic and widespread across applications like video conferencing and social media. Although state-of-the-art detectors achieve high accuracy on standard benchmarks, their heavy computational cost hinders...","url_abs":"https://arxiv.org/abs/2508.20449","url_pdf":"https://arxiv.org/pdf/2508.20449v1","authors":"[\"Libo Lv\",\"Tianyi Wang\",\"Mengxiao Huang\",\"Ruixia Liu\",\"Yinglong Wang\"]","published":"2025-08-28T05:55:28Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}