在视频特征隐空间实现隐私保护，不改模型也能去敏感信息。
Privacy Beyond Pixels: Latent Anonymization for Privacy-Preserving Video Understanding
- 用轻量级适配模块在隐空间剥离隐私信息，无需重训练模型。
- 隐私泄露降低35%，动作识别等任务性能接近原始模型。
- 可缓解性别偏见，适合对公平性要求高的视频理解场景。
我们提出一种全新的视频基础模型隐私保护方法，完全在隐空间中操作。尽管时空特征增强了视频内容的理解能力，但共享或存储这些特征会意外暴露肤色、性别、着装等敏感信息。现有方法聚焦于像素级匿名化，需重新训练整个模型，且仅适用于特定任务，难以适配当前视频基础模型。为此，我们引入轻量级匿名化适配模块（AAM），可即插即用地作用于冻结的视频编码器，在最小化微调计算负担的前提下，从视频特征中移除隐私信息。框架采用三项新设计的训练目标：(1) 剪辑级别的自监督隐私目标，降低静态剪辑间的互信息；(2) 联合训练目标，保留已见任务的性能；(3) 隐空间一致性损失，提升未见任务的泛化能力。大量评估显示，隐私泄露显著减少35%，同时在多个下游任务上保持近基线性能：动作识别（Kinetics400, UCF101, HMDB51）、时间动作检测（THUMOS14）和异常检测（UCF-Crime）。我们还分析了对敏感时间属性的匿名化效果，并提出了新的性别偏见评估协议，证明该方法有效缓解偏见，促进更公平的视频理解。
原文摘要 · Abstract (English)
We introduce a novel formulation of visual privacy preservation for video foundation models that operates entirely in the latent space. While spatio-temporal features learned by foundation models have deepened general understanding of video content, sharing or storing these extracted visual features for downstream tasks inadvertently reveals sensitive personal information like skin color, gender, or clothing. Current privacy preservation methods focus on input-pixel-level anonymization, which requires retraining the entire utility video model and results in task-specific anonymization, making them unsuitable for recent video foundational models. To address these challenges, we introduce a lightweight Anonymizing Adapter Module (AAM) that removes private information from video features while retaining general task utility. AAM can be applied in a plug-and-play fashion to frozen video encoders, minimizing the computational burden of finetuning and re-extracting features. Our framework employs three newly designed training objectives: (1) a clip-level self-supervised privacy objective to reduce mutual information between static clips, (2) a co-training objective to retain utility across seen tasks, and (3) a latent consistency loss for generalization on unseen tasks. Our extensive evaluations demonstrate a significant 35% reduction in privacy leakage while maintaining near-baseline utility performance across various downstream tasks: Action Recognition (Kinetics400, UCF101, HMDB51), Temporal Action Detection (THUMOS14), and Anomaly Detection (UCF-Crime). We also provide an analysis on anonymization for sensitive temporal attribute recognition. Additionally, we propose new protocols for assessing gender bias in action recognition models, showing that our method effectively mitigates such biases and promotes more equitable video understanding. https://joefioresi718.github.io/SPLAVU_webpage/
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。