# Real-Time Privacy Preservation for Robot Visual Perception

arXiv: https://arxiv.org/abs/2505.05519 · HTML: https://mlsanity.com/paper/2505.05519/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 38 references that are in the map.
- First posted on arXiv 8 May 2025.

## Builds on (most cited first, 18 of 18)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [Simple Online and Realtime Tracking with a Deep Association Metric](https://mlsanity.com/paper/1703.07402/) (2017)
- [Simple Online and Realtime Tracking](https://mlsanity.com/paper/1602.00763/) (2016)
- [YOLO-World: Real-Time Open-Vocabulary Object Detection](https://mlsanity.com/paper/2401.17270/) (2024)
- [YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information](https://mlsanity.com/paper/2402.13616/) (2024)
- [A Robust Real-Time Automatic License Plate Recognition Based on the YOLO Detector](https://mlsanity.com/paper/1802.09567/) (2018)
- [GEMEL: Model Merging for Memory-Efficient, Real-Time Video Analytics at the Edge](https://mlsanity.com/paper/2201.07705/) (2022)
- [REVAMP2T: Real-time Edge Video Analytics for Multi-camera Privacy-aware Pedestrian Tracking](https://mlsanity.com/paper/1911.09217/) (2019)
- [Know Where You're Uncertain When Planning with Multimodal Foundation Models: A Formal Framework](https://mlsanity.com/paper/2411.01639/) (2024)
- [Fine-Tuning Language Models Using Formal Methods Feedback](https://mlsanity.com/paper/2310.18239/) (2023)
- [Specification-Driven Video Search via Foundation Models and Formal Verification](https://mlsanity.com/paper/2309.10171/) (2023)
- [We'll Fix it in Post: Improving Text-to-Video Generation with Neuro-Symbolic Feedback](https://mlsanity.com/paper/2504.17180/) (2025)
- [Neuro-Symbolic Evaluation of Text-to-Video Models using Formal Verification](https://mlsanity.com/paper/2411.16718/) (2024)
- [Privid: Practical, Privacy-Preserving Video Analytics Queries](https://mlsanity.com/paper/2106.12083/) (2021)
- [Zooming Into Video Conferencing Privacy and Security Threats](https://mlsanity.com/paper/2007.01059/) (2020)
- [Minor Privacy Protection Through Real-time Video Processing at the Edge](https://mlsanity.com/paper/2005.01178/) (2020)

## Built on by (most cited first, 2 of 2)

- [A Challenge to Build Neuro-Symbolic Video Agents](https://mlsanity.com/paper/2505.13851/) (2025)
- [Position: Embodied AI Requires a Privacy-Utility Trade-off](https://mlsanity.com/paper/2605.05017/) (2026)

## Abstract (arXiv)

Many robots (e.g., iRobot's Roomba) operate based on visual observations from live video streams, and such observations may inadvertently include privacy-sensitive objects, such as personal identifiers. Existing approaches for preserving privacy rely on deep learning models, differential privacy, or cryptography. They lack guarantees for the complete concealment of all sensitive objects. Guaranteeing concealment requires post-processing techniques and thus is inadequate for real-time video streams. We develop a method for privacy-constrained video streaming, PCVS, that conceals sensitive objects within real-time video streams. PCVS takes a logical specification constraining the existence of privacy-sensitive objects, e.g., never show faces when a person exists. It uses a detection model to evaluate the existence of these objects in each incoming frame. Then, it blurs out a subset of objects such that the existence of the remaining objects satisfies the specification. We then propose a conformal prediction approach to (i) establish a theoretical lower bound on the probability of the existence of these objects in a sequence of frames satisfying the specification and (ii) update the bound with the arrival of each subsequent frame. Quantitative evaluations show that PCVS achieves over 95 percent specification satisfaction rate in multiple datasets, significantly outperforming other methods. The satisfaction rate is consistently above the theoretical bounds across all datasets, indicating that the established bounds hold. Additionally, we deploy PCVS on robots in real-time operation and show that the robots operate normally without being compromised when PCVS conceals objects.