# Privacy Beyond Pixels: Latent Anonymization for Privacy-Preserving Video Understanding

arXiv: https://arxiv.org/abs/2511.08666 · HTML: https://mlsanity.com/paper/2511.08666/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 48 of its 73 references that are in the map.
- First posted on arXiv 11 Nov 2025.

## Builds on (most cited first, 30 of 48)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis](https://mlsanity.com/paper/1604.02808/) (2016)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [Revisiting Feature Prediction for Learning Visual Representations from Video](https://mlsanity.com/paper/2404.08471/) (2024)
- [VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://mlsanity.com/paper/2303.16727/) (2023)
- [InternVideo: General Video Foundation Models via Generative and Discriminative Learning](https://mlsanity.com/paper/2212.03191/) (2022)
- [Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints](https://mlsanity.com/paper/1707.09457/) (2017)
- [Differentially Private Fine-tuning of Language Models](https://mlsanity.com/paper/2110.06500/) (2021)
- [TriDet: Temporal Action Detection with Relative Boundary Modeling](https://mlsanity.com/paper/2303.07347/) (2023)
- [TCLR: Temporal Contrastive Learning for Video Representation](https://mlsanity.com/paper/2101.07974/) (2021)
- [Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition](https://mlsanity.com/paper/1912.05534/) (2019)
- [Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases](https://mlsanity.com/paper/2010.15052/) (2020)
- [Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Images](https://mlsanity.com/paper/1703.10660/) (2017)
- [FedPrompt: Communication-Efficient and Privacy Preserving Prompt Tuning in Federated Learning](https://mlsanity.com/paper/2208.12268/) (2022)
- [MGFN: Magnitude-Contrastive Glance-and-Focus Network for Weakly-Supervised Video Anomaly Detection](https://mlsanity.com/paper/2211.15098/) (2022)
- [Predictive Inequity in Object Detection](https://mlsanity.com/paper/1902.11097/) (2019)
- [Learning to Anonymize Faces for Privacy Preserving Action Detection](https://mlsanity.com/paper/1803.11556/) (2018)
- [FACET: Fairness in Computer Vision Evaluation Benchmark](https://mlsanity.com/paper/2309.00035/) (2023)
- [SPAct: Self-supervised Privacy Preservation for Action Recognition](https://mlsanity.com/paper/2203.15205/) (2022)
- [Motion-aware Contrastive Video Representation Learning via Foreground-background Merging](https://mlsanity.com/paper/2109.15130/) (2021)
- [Time-Equivariant Contrastive Video Representation Learning](https://mlsanity.com/paper/2112.03624/) (2021)

## Built on by (most cited first, 1 of 1)

- [Privacy-Aware Synthetic Video Benchmarking and Relational Evaluation for Worker-Under-Suspended-Load Detection](https://mlsanity.com/paper/2607.16351/) (2026)

## Abstract (arXiv)

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/