AI 中文总结
V-FIND框架发现视频伪造检测器的稀疏判别神经元，构建取证子空间，在冻结骨干仅训练轻量级分类器时，于多基准上实现强劲检测性能，为理解检测器内在能力提供新视角。
AI 中文摘要
随着生成视频的逼真度不断提升，可靠的视频伪造检测愈发重要。现有研究通常将视频伪造检测器作为黑盒进行优化和使用，而其内部潜藏的伪造判别知识却大多未被探索。我们不再继续依赖资源密集型的全模型重新训练来稳步提升检测性能，而是提出疑问：视频伪造检测是否也可通过揭示并激活检测器内的稀疏取证知识来实现。我们发现，伪造判别知识并非均匀分布在整个表示空间，而是集中于一组稀疏的功能特化神经元中。基于这一见解，我们提出视频伪造内在神经元发现（V-FIND）框架。V-FIND首先定位出真实视频与伪造视频之间存在显著差异的关键层，随后识别出始终携带伪造判别信号的潜在锚定神经元，将其组织成紧凑的取证子空间。在冻结原始骨干网络、仅训练轻量级线性分类器的情况下，该子空间在多个生成视频的外部基准测试中仍展现出强劲的检测性能。进一步的神经元干预实验为所发现神经元的功能特异性提供了直接证据。总体而言，这些结果表明视频伪造检测器包含稀疏、可提取且可复用的伪造判别知识，为理解和利用其内在取证能力提供了新视角。
英文摘要
As generated videos become increasingly realistic, reliable video forgery detection is increasingly important. Existing studies typically optimize and use video forgery detectors as black boxes, while the latent forgery-discriminative knowledge inside them remains largely unexplored. Instead of continuing to rely on resource-intensive full-model retraining to steadily improve detection performance, we ask whether video forgery detection can also be achieved by uncovering and activating sparse forensic knowledge within the detector. We find that forgery-discriminative knowledge is not uniformly distributed across the full representation space, but is concentrated in a sparse set of functionally specialized neurons. Based on this insight, we propose a video forgery-intrinsic neuron discovery (V-FIND) framework. V-FIND first localizes critical layers that exhibit pronounced discrepancies between real and forged videos, and then identifies latent anchor neurons that consistently carry forgery-discriminative signals, organizing them into a compact forensic subspace. With the original backbone frozen and only a lightweight linear classifier trained, this subspace still delivers strong detection performance across multiple external benchmarks for generated videos. Further neuron intervention experiments provide direct evidence for the functional specificity of the discovered neurons. Overall, these results suggest that video forgery detectors contain sparse, extractable, and reusable forgery-discriminative knowledge, offering a new perspective on understanding and exploiting their intrinsic forensic capability.
Comments12 pages, 12 figures. Under review
