Privacy Blur: Quantifying Privacy and Utility for Image Data Release
- URL: http://arxiv.org/abs/2512.16086v1
- Date: Thu, 18 Dec 2025 02:01:17 GMT
- Title: Privacy Blur: Quantifying Privacy and Utility for Image Data Release
- Authors: Saeed Mahloujifar, Narine Kokhlikyan, Chuan Guo, Kamalika Chaudhuri,
- Abstract summary: We show that practical implementations of Gaussian blurring are reversible enough to break privacy.<n>We take a closer look at the privacy-utility tradeoffs offered by three other obfuscation algorithms.<n> pixelization and noise addition offer both privacy and utility for a number of computer vision tasks.
- Score: 48.64095568151945
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Image data collected in the wild often contains private information such as faces and license plates, and responsible data release must ensure that this information stays hidden. At the same time, released data should retain its usefulness for model-training. The standard method for private information obfuscation in images is Gaussian blurring. In this work, we show that practical implementations of Gaussian blurring are reversible enough to break privacy. We then take a closer look at the privacy-utility tradeoffs offered by three other obfuscation algorithms -- pixelization, pixelization and noise addition (DP-Pix), and cropping. Privacy is evaluated by reversal and discrimination attacks, while utility by the quality of the learnt representations when the model is trained on data with obfuscated faces. We show that the most popular industry-standard method, Gaussian blur is the least private of the four -- being susceptible to reversal attacks in its practical low-precision implementations. In contrast, pixelization and pixelization plus noise addition, when used at the right level of granularity, offer both privacy and utility for a number of computer vision tasks. We make our proposed methods together with suggested parameters available in a software package called Privacy Blur.
Related papers
- Activity Recognition on Avatar-Anonymized Datasets with Masked Differential Privacy [64.32494202656801]
Privacy-preserving computer vision is an important emerging problem in machine learning and artificial intelligence.<n>We present anonymization pipeline that replaces sensitive human subjects in video datasets with synthetic avatars within context.<n>We also proposeMaskDP to protect non-anonymized but privacy sensitive background information.
arXiv Detail & Related papers (2024-10-22T15:22:53Z) - ConfounderGAN: Protecting Image Data Privacy with Causal Confounder [85.6757153033139]
We propose ConfounderGAN, a generative adversarial network (GAN) that can make personal image data unlearnable to protect the data privacy of its owners.
Experiments are conducted in six image classification datasets, consisting of three natural object datasets and three medical datasets.
arXiv Detail & Related papers (2022-12-04T08:49:14Z) - On the Design of Privacy-Aware Cameras: a Study on Deep Neural Networks [0.7646713951724011]
This paper studies the effect of camera distortions on data protection.
We build a privacy-aware camera that cannot extract personal information such as license plate numbers.
At the same time, we ensure that useful non-sensitive data can still be extracted from distorted images.
arXiv Detail & Related papers (2022-08-24T08:45:31Z) - Smooth Anonymity for Sparse Graphs [69.1048938123063]
differential privacy has emerged as the gold standard of privacy, however, when it comes to sharing sparse datasets.
In this work, we consider a variation of $k$-anonymity, which we call smooth-$k$-anonymity, and design simple large-scale algorithms that efficiently provide smooth-$k$-anonymity.
arXiv Detail & Related papers (2022-07-13T17:09:25Z) - OPOM: Customized Invisible Cloak towards Face Privacy Protection [58.07786010689529]
We investigate the face privacy protection from a technology standpoint based on a new type of customized cloak.
We propose a new method, named one person one mask (OPOM), to generate person-specific (class-wise) universal masks.
The effectiveness of the proposed method is evaluated on both common and celebrity datasets.
arXiv Detail & Related papers (2022-05-24T11:29:37Z) - Privacy Enhancement for Cloud-Based Few-Shot Learning [4.1579007112499315]
We study the privacy enhancement for the few-shot learning in an untrusted environment, e.g., the cloud.
We propose a method that learns privacy-preserved representation through the joint loss.
The empirical results show how privacy-performance trade-off can be negotiated for privacy-enhanced few-shot learning.
arXiv Detail & Related papers (2022-05-10T18:48:13Z) - InfoScrub: Towards Attribute Privacy by Targeted Obfuscation [77.49428268918703]
We study techniques that allow individuals to limit the private information leaked in visual data.
We tackle this problem in a novel image obfuscation framework.
We find our approach generates obfuscated images faithful to the original input images, and additionally increase uncertainty by 6.2$times$ (or up to 0.85 bits) over the non-obfuscated counterparts.
arXiv Detail & Related papers (2020-05-20T19:48:04Z) - Privacy-Preserving Image Classification in the Local Setting [17.375582978294105]
Local Differential Privacy (LDP) brings us a promising solution, which allows the data owners to randomly perturb their input to provide the plausible deniability of the data before releasing.
In this paper, we consider a two-party image classification problem, in which data owners hold the image and the untrustworthy data user would like to fit a machine learning model with these images as input.
We propose a supervised image feature extractor, DCAConv, which produces an image representation with scalable domain size.
arXiv Detail & Related papers (2020-02-09T01:25:52Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.