通过分析模型内部潜在表示，实时高效识别生成视频中的色情内容。
Latent Space Probing for Adult Content Detection in Video Generative Models
- 在CogVideoX的去噪潜空间中插入轻量级分类器，实现内容检测。
- 在1.1万段视频上达97.29%的F1分数，延迟仅4-6毫秒。
- 适合需要低延迟、高精度的内容安全系统开发者使用。
AI视频生成系统的快速普及带来了内容审核的重大挑战，尤其在成人及性暗示内容方面。现有方法主要基于提示词或解码后的像素空间输出，对生成过程中的内部表征无法感知。本文提出一种新型潜空间探测框架，拦截CogVideoX视频扩散模型推理时产生的去噪潜表示，并附加轻量级分类器实现实时成人内容检测。为此，我们构建了一个大规模二分类数据集，包含11039段十秒视频片段（5086段违规，5953段非违规），数据来源为成人网站和YouTube。引入两种轻量级探测分类器架构，进行训练与评估。结果表明，潜空间信号蕴含强区分特征，可在保留测试集上达到97.29% F1分数，计算开销仅为4-6毫秒。研究显示，潜空间探测能同时提升检测性能与效率。
原文摘要 · Abstract (English)
The rapid proliferation of AI-powered video generation systems has introduced significant challenges in content moderation, particularly with respect to adult and sexually explicit material. Existing detection methods operate on either prompts or decoded pixel-space outputs. Therefore, both approaches are blind to the rich internal representations formed during generation. In this paper, we propose a novel latent space probing framework that intercepts the denoised latent representations produced by the CogVideoX video diffusion model during inference and attaches lightweight classifiers to perform real-time adult content detection. To support this work, we construct a large-scale binary dataset of 11039 ten-second video clips (5086 violating, 5953 non-violating) sourced from adult websites and YouTube respectively. We introduce two lightweight probing classifier architectures. We train and evaluate it on the dataset. Our work demonstrates that latent-space signals encode strong discriminative features for harmful content detection, achieving 97.29% F1 on our held-out test set with an overhead in the 4-6ms range. Our results suggest that probing the latent space results in improvements in both detection performance as well as cost.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。