# VPD-100K: Towards Generalizable and Fine-grained Visual Privacy Protection

arXiv: https://arxiv.org/abs/2605.10229 · HTML: https://mlsanity.com/paper/2605.10229/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 57 references that are in the map.
- First posted on arXiv 11 May 2026.

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

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [YOLOv10: Real-Time End-to-End Object Detection](https://mlsanity.com/paper/2405.14458/) (2024)
- [YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information](https://mlsanity.com/paper/2402.13616/) (2024)
- [WIDER FACE: A Face Detection Benchmark](https://mlsanity.com/paper/1511.06523/) (2015)
- [The Secrets of Salient Object Segmentation](https://mlsanity.com/paper/1406.2807/) (2014)
- [DEIM: DETR with Improved Matching for Fast Convergence](https://mlsanity.com/paper/2412.04234/) (2024)
- [Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism](https://mlsanity.com/paper/2309.11331/) (2023)
- [CLIP2Protect: Protecting Facial Privacy using Text-Guided Makeup via Adversarial Latent Search](https://mlsanity.com/paper/2306.10008/) (2023)
- [MIDV-500: A Dataset for Identity Documents Analysis and Recognition on Mobile Devices in Video Stream](https://mlsanity.com/paper/1807.05786/) (2018)
- [Personal Privacy Protection via Irrelevant Faces Tracking and Pixelation in Video Live Streaming](https://mlsanity.com/paper/2101.01060/) (2021)
- [FBRT-YOLO: Faster and Better for Real-Time Aerial Image Detection](https://mlsanity.com/paper/2504.20670/) (2025)
- [Visual Content Privacy Protection: A Survey](https://mlsanity.com/paper/2303.16552/) (2023)
- [LiveSeg: Unsupervised Multimodal Temporal Segmentation of Long Livestream Videos](https://mlsanity.com/paper/2210.05840/) (2022)
- [Privacy Bills of Materials: A Transparent Privacy Information Inventory for Collaborative Privacy Notice Generation in Mobile App Development](https://mlsanity.com/paper/2501.01131/) (2025)
- [LiveVV: Human-Centered Live Volumetric Video Streaming System](https://mlsanity.com/paper/2310.08205/) (2023)
- [Explaining models relating objects and privacy](https://mlsanity.com/paper/2405.01646/) (2024)
- [A First Look at Privacy Risks of Android Task-executable Voice Assistant Applications](https://mlsanity.com/paper/2509.23680/) (2025)
- [Demystifying Hidden Sensitive Operations in Android apps](https://mlsanity.com/paper/2210.10997/) (2022)
- [Characterizing Sensor Leaks in Android Apps](https://mlsanity.com/paper/2201.06235/) (2022)
- [Beyond Visual Appearances: Privacy-sensitive Objects Identification via Hybrid Graph Reasoning](https://mlsanity.com/paper/2406.12736/) (2024)
- [Image Privacy Protection: A Survey](https://mlsanity.com/paper/2412.15228/) (2024)

## Abstract (arXiv)

Privacy protection has become a critical requirement in the era of ubiquitous visual data sharing, imposing higher demands on efficient and robust privacy detection algorithms. However, current robust detection models are severely hindered by the lack of comprehensive datasets. Existing privacy-oriented datasets often suffer from limited scale, coarse-grained annotations, and narrow domain coverage, failing to capture the intricate details of sensitive information in realworld environments. To bridge this gap, we present a large-scale, fine-grained Visual Privacy Dataset (VPD-100K), designed to facilitate generalized privacy detection. We establish a holistic taxonomy comprising four primary domains: Human Presence, On-Screen Personally Identifiable Information (PII), Physical Identifiers, and Location Indicators, containing 100,000 images annotated with 33 fine-grained classes and over 190,000 object instances. Statistical analysis reveals that our dataset features long-tailed distributions, small object scales, and high visual complexity. These characteristics make the dataset particularly valuable for demanding, unconstrained applications such as live streaming, where actors frequently face unintentional, realtime information leakage. Furthermore, we design an effective frequency-enhanced lightweight module consisting of frequency-domain attention fusion and adaptive spectral gating mechanism that breaks the limitations of spatial pixel intensity to better capture the subtle details of sensitive information. Extensive experiments conducted on both diverse image and streaming videos benchmarks consistently demonstrate the effectiveness of our VPD-100K dataset and the wellcurated frequency mechanism. The code and dataset are available at https://vpd-100k.github.io/.