# LDFA: Latent Diffusion Face Anonymization for Self-driving Applications

arXiv: https://arxiv.org/abs/2302.08931 · HTML: https://mlsanity.com/paper/2302.08931/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models.
- Builds on 27 of its 36 references that are in the map.
- First posted on arXiv 17 Feb 2023.

## Placed in

- Diffusion models / [Robustness, privacy and adversarial aspects](https://mlsanity.com/diffusion/robustness-privacy-and-adversarial-aspects/)

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [DiffWave: A Versatile Diffusion Model for Audio Synthesis](https://mlsanity.com/paper/2009.09761/) (2020)
- [Diffusion Probabilistic Models for 3D Point Cloud Generation](https://mlsanity.com/paper/2103.01458/) (2021)
- [Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting](https://mlsanity.com/paper/2301.00493/) (2023)
- [A2D2: Audi Autonomous Driving Dataset](https://mlsanity.com/paper/2004.06320/) (2020)
- [RetinaFace: Single-stage Dense Face Localisation in the Wild](https://mlsanity.com/paper/1905.00641/) (2019)
- [DSFD: Dual Shot Face Detector](https://mlsanity.com/paper/1810.10220/) (2018)
- [DeepPrivacy: A Generative Adversarial Network for Face Anonymization](https://mlsanity.com/paper/1909.04538/) (2019)
- [CIAGAN: Conditional Identity Anonymization Generative Adversarial Networks](https://mlsanity.com/paper/2005.09544/) (2020)
- [Continuous Surface Embeddings](https://mlsanity.com/paper/2011.12438/) (2020)
- [DeepPrivacy2: Towards Realistic Full-Body Anonymization](https://mlsanity.com/paper/2211.09454/) (2022)
- [Vulnerable road user detection: state-of-the-art and open challenges](https://mlsanity.com/paper/1902.03601/) (2019)
- [Safe Fakes: Evaluating Face Anonymizers for Face Detectors](https://mlsanity.com/paper/2104.11721/) (2021)

## Built on by (most cited first, 21 of 21)

- [Self-Consuming Generative Models Go MAD](https://mlsanity.com/paper/2307.01850/) (2023)
- [Dataset Enhancement with Instance-Level Augmentations](https://mlsanity.com/paper/2406.08249/) (2024)
- [EgoBlur: Responsible Innovation in Aria](https://mlsanity.com/paper/2308.13093/) (2023)
- [Face De-identification: State-of-the-art Methods and Comparative Studies](https://mlsanity.com/paper/2411.09863/) (2024)
- [NullFace: Training-Free Localized Face Anonymization](https://mlsanity.com/paper/2503.08478/) (2025)
- [Context-Aware Full Body Anonymization using Text-to-Image Diffusion Models](https://mlsanity.com/paper/2410.08551/) (2024)
- [My Body My Choice: Human-Centric Full-Body Anonymization](https://mlsanity.com/paper/2406.09553/) (2024)
- [Bounding Box-Guided Diffusion for Synthesizing Industrial Images and Segmentation Map](https://mlsanity.com/paper/2505.03623/) (2025)
- [Anonymization Prompt Learning for Facial Privacy-Preserving Text-to-Image Generation](https://mlsanity.com/paper/2405.16895/) (2024)
- [FAKER: Full-body Anonymization with Human Keypoint Extraction for Real-time Video Deidentification](https://mlsanity.com/paper/2408.11829/) (2024)
- [SVIA: A Street View Image Anonymization Framework for Self-Driving Applications](https://mlsanity.com/paper/2501.09393/) (2025)
- [Reverse Personalization](https://mlsanity.com/paper/2512.22984/) (2025)
- [Towards Context-Aware Image Anonymization with Multi-Agent Reasoning](https://mlsanity.com/paper/2603.27817/) (2026)
- [Trustworthy Large Models in Vision: A Survey](https://mlsanity.com/paper/2311.09680/) (2023)
- [Assessing the Use of Face Swapping Methods as Face Anonymizers in Videos](https://mlsanity.com/paper/2505.20985/) (2025)
- [Facial Attribute Based Text Guided Face Anonymization](https://mlsanity.com/paper/2505.21002/) (2025)
- [Face anonymization preserving facial expressions and photometric realism](https://mlsanity.com/paper/2603.17567/) (2026)
- [Generative Anonymization in Event Streams](https://mlsanity.com/paper/2604.12803/) (2026)
- [ReGenHuman: Re-Generating Human Appearances for Realistic Full-Body Video Anonymization](https://mlsanity.com/paper/2606.14972/) (2026)
- [HYDRO: Towards Non-Reversible Face De-Identification Using a High-Fidelity Hybrid Diffusion and Target-Oriented Approach](https://mlsanity.com/paper/2609.27011/) (2026)
- [Adversarial Attacks and Identity Leakage in De-Identification Systems: An Empirical Study](https://mlsanity.com/paper/2609.27022/) (2026)

## Abstract (arXiv)

In order to protect vulnerable road users (VRUs), such as pedestrians or cyclists, it is essential that intelligent transportation systems (ITS) accurately identify them. Therefore, datasets used to train perception models of ITS must contain a significant number of vulnerable road users. However, data protection regulations require that individuals are anonymized in such datasets. In this work, we introduce a novel deep learning-based pipeline for face anonymization in the context of ITS. In contrast to related methods, we do not use generative adversarial networks (GANs) but build upon recent advances in diffusion models. We propose a two-stage method, which contains a face detection model followed by a latent diffusion model to generate realistic face in-paintings. To demonstrate the versatility of anonymized images, we train segmentation methods on anonymized data and evaluate them on non-anonymized data. Our experiment reveal that our pipeline is better suited to anonymize data for segmentation than naive methods and performes comparably with recent GAN-based methods. Moreover, face detectors achieve higher mAP scores for faces anonymized by our method compared to naive or recent GAN-based methods.