Protecting User Privacy in Online Settings via Supervised Learning
- URL: http://arxiv.org/abs/2304.02870v1
- Date: Thu, 6 Apr 2023 05:20:16 GMT
- Title: Protecting User Privacy in Online Settings via Supervised Learning
- Authors: Alexandru Rusescu, Brooke Lampe, and Weizhi Meng
- Abstract summary: We design an intelligent approach to online privacy protection that leverages supervised learning.
By detecting and blocking data collection that might infringe on a user's privacy, we can restore a degree of digital privacy to the user.
- Score: 69.38374877559423
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Companies that have an online presence-in particular, companies that are
exclusively digital-often subscribe to this business model: collect data from
the user base, then expose the data to advertisement agencies in order to turn
a profit. Such companies routinely market a service as "free", while
obfuscating the fact that they tend to "charge" users in the currency of
personal information rather than money. However, online companies also gather
user data for more principled purposes, such as improving the user experience
and aggregating statistics. The problem is the sale of user data to third
parties. In this work, we design an intelligent approach to online privacy
protection that leverages supervised learning. By detecting and blocking data
collection that might infringe on a user's privacy, we can restore a degree of
digital privacy to the user. In our evaluation, we collect a dataset of network
requests and measure the performance of several classifiers that adhere to the
supervised learning paradigm. The results of our evaluation demonstrate the
feasibility and potential of our approach.
Related papers
- FT-PrivacyScore: Personalized Privacy Scoring Service for Machine Learning Participation [4.772368796656325]
In practice, controlled data access remains a mainstream method for protecting data privacy in many industrial and research environments.
We developed the demo prototype FT-PrivacyScore to show that it's possible to efficiently and quantitatively estimate the privacy risk of participating in a model fine-tuning task.
arXiv Detail & Related papers (2024-10-30T02:41:26Z) - Towards a User Privacy-Aware Mobile Gaming App Installation Prediction
Model [0.8602553195689513]
We investigate the process of predicting a mobile gaming app installation from the point of view of a demand-side platform.
We explore the trade-off between privacy preservation and model performance.
We conclude that privacy-aware models might still preserve significant capabilities.
arXiv Detail & Related papers (2023-02-07T09:14:59Z) - Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining [75.25943383604266]
We question whether the use of large Web-scraped datasets should be viewed as differential-privacy-preserving.
We caution that publicizing these models pretrained on Web data as "private" could lead to harm and erode the public's trust in differential privacy as a meaningful definition of privacy.
We conclude by discussing potential paths forward for the field of private learning, as public pretraining becomes more popular and powerful.
arXiv Detail & Related papers (2022-12-13T10:41:12Z) - Certified Data Removal in Sum-Product Networks [78.27542864367821]
Deleting the collected data is often insufficient to guarantee data privacy.
UnlearnSPN is an algorithm that removes the influence of single data points from a trained sum-product network.
arXiv Detail & Related papers (2022-10-04T08:22:37Z) - Challenges and approaches to privacy preserving post-click conversion
prediction [3.4071263815701336]
We provide an overview of the challenges and constraints when learning conversion models in this setting.
We introduce a novel approach for training these models that makes use of post-ranking signals.
We show using offline experiments on real world data that it outperforms a model relying on opt-in data alone.
arXiv Detail & Related papers (2022-01-29T21:36:01Z) - Preventing Unauthorized Use of Proprietary Data: Poisoning for Secure
Dataset Release [52.504589728136615]
We develop a data poisoning method by which publicly released data can be minimally modified to prevent others from train-ing models on it.
We demonstrate the success of our approach onImageNet classification and on facial recognition.
arXiv Detail & Related papers (2021-02-16T19:12:34Z) - PCAL: A Privacy-preserving Intelligent Credit Risk Modeling Framework
Based on Adversarial Learning [111.19576084222345]
This paper proposes a framework of Privacy-preserving Credit risk modeling based on Adversarial Learning (PCAL)
PCAL aims to mask the private information inside the original dataset, while maintaining the important utility information for the target prediction task performance.
Results indicate that PCAL can learn an effective, privacy-free representation from user data, providing a solid foundation towards privacy-preserving machine learning for credit risk analysis.
arXiv Detail & Related papers (2020-10-06T07:04:59Z) - Security and Privacy Preserving Deep Learning [2.322461721824713]
Massive data collection required for deep learning presents obvious privacy issues.
Users personal, highly sensitive data such as photos and voice recordings are kept indefinitely by the companies that collect it.
Deep neural networks are susceptible to various inference attacks as they remember information about their training data.
arXiv Detail & Related papers (2020-06-23T01:53:46Z) - Utility-aware Privacy-preserving Data Releasing [7.462336024223669]
We propose a two-step perturbation-based privacy-preserving data releasing framework.
First, certain predefined privacy and utility problems are learned from the public domain data.
We then leverage the learned knowledge to precisely perturb the data owners' data into privatized data.
arXiv Detail & Related papers (2020-05-09T05:32:46Z) - Beyond privacy regulations: an ethical approach to data usage in
transportation [64.86110095869176]
We describe how Federated Machine Learning can be applied to the transportation sector.
We see Federated Learning as a method that enables us to process privacy-sensitive data, while respecting customer's privacy.
arXiv Detail & Related papers (2020-04-01T15:10:12Z)
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.