# StegaVAR: Privacy-Preserving Video Action Recognition via Steganographic Domain Analysis

arXiv: https://arxiv.org/abs/2512.12586 · HTML: https://mlsanity.com/paper/2512.12586/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 55 references that are in the map.
- First posted on arXiv 14 Dec 2025.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (2017)
- [NICE: Non-linear Independent Components Estimation](https://mlsanity.com/paper/1410.8516/) (2014)
- [HiDDeN: Hiding Data With Deep Networks](https://mlsanity.com/paper/1807.09937/) (2018)
- [Video Instance Segmentation](https://mlsanity.com/paper/1905.04804/) (2019)
- [Temporal Segment Networks for Action Recognition in Videos](https://mlsanity.com/paper/1705.02953/) (2017)
- [Human Action Recognition from Various Data Modalities: A Review](https://mlsanity.com/paper/2012.11866/) (2020)
- [Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Images](https://mlsanity.com/paper/1703.10660/) (2017)
- [FusionMamba: Dynamic Feature Enhancement for Multimodal Image Fusion with Mamba](https://mlsanity.com/paper/2404.09498/) (2024)
- [SteganoGAN: High Capacity Image Steganography with GANs](https://mlsanity.com/paper/1901.03892/) (2019)
- [Learning to Anonymize Faces for Privacy Preserving Action Detection](https://mlsanity.com/paper/1803.11556/) (2018)
- [SPAct: Self-supervised Privacy Preservation for Action Recognition](https://mlsanity.com/paper/2203.15205/) (2022)
- [Privacy-Preserving Human Activity Recognition from Extreme Low Resolution](https://mlsanity.com/paper/1604.03196/) (2016)
- [STPrivacy: Spatio-Temporal Privacy-Preserving Action Recognition](https://mlsanity.com/paper/2301.03046/) (2023)
- [Large-capacity and Flexible Video Steganography via Invertible Neural Network](https://mlsanity.com/paper/2304.12300/) (2023)
- [Human Pose Estimation on Privacy-Preserving Low-Resolution Depth Images](https://mlsanity.com/paper/2007.08340/) (2020)
- [Privacy-Preserving Action Recognition for Smart Hospitals using Low-Resolution Depth Images](https://mlsanity.com/paper/1811.09950/) (2018)
- [Safeguarding Medical Image Segmentation Datasets against Unauthorized Training via Contour- and Texture-Aware Perturbations](https://mlsanity.com/paper/2403.14250/) (2024)
- [MaSS: Multi-attribute Selective Suppression](https://mlsanity.com/paper/2210.09904/) (2022)
- [Balancing Privacy and Action Performance: A Penalty-Driven Approach to Image Anonymization](https://mlsanity.com/paper/2504.14301/) (2025)

## 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)

Despite the rapid progress of deep learning in video action recognition (VAR) in recent years, privacy leakage in videos remains a critical concern. Current state-of-the-art privacy-preserving methods often rely on anonymization. These methods suffer from (1) low concealment, where producing visually distorted videos that attract attackers' attention during transmission, and (2) spatiotemporal disruption, where degrading essential spatiotemporal features for accurate VAR. To address these issues, we propose StegaVAR, a novel framework that embeds action videos into ordinary cover videos and directly performs VAR in the steganographic domain for the first time. Throughout both data transmission and action analysis, the spatiotemporal information of hidden secret video remains complete, while the natural appearance of cover videos ensures the concealment of transmission. Considering the difficulty of steganographic domain analysis, we propose Secret Spatio-Temporal Promotion (STeP) and Cross-Band Difference Attention (CroDA) for analysis within the steganographic domain. STeP uses the secret video to guide spatiotemporal feature extraction in the steganographic domain during training. CroDA suppresses cover interference by capturing cross-band semantic differences. Experiments demonstrate that StegaVAR achieves superior VAR and privacy-preserving performance on widely used datasets. Moreover, our framework is effective for multiple steganographic models.