Semantics-Preserved Distortion for Personal Privacy Protection

01/04/2022
by   Letian Peng, et al.
0

Privacy protection is an important and concerning topic in Federated Learning, especially for Natural Language Processing. In client devices, a large number of texts containing personal information are produced by users every day. As the direct application of information from users is likely to invade personal privacy, many methods have been proposed in Federated Learning to block the center model from the raw information in client devices. In this paper, we try to do this more linguistically via distorting the text while preserving the semantics. In practice, we leverage a recently proposed metric, Neighboring Distribution Divergence, to evaluate the semantic preservation during the distortion. Based on the metric, we propose two frameworks for semantics-preserved distortion, a generative one and a substitutive one. Due to the lack of privacy-related tasks in the current Natural Language Processing field, we conduct experiments on named entity recognition and constituency parsing. Results from our experiments show the plausibility and efficiency of our distortion as a method for personal privacy protection.

READ FULL TEXT

page 2

page 6

research
07/27/2021

Federated Learning Meets Natural Language Processing: A Survey

Federated Learning aims to learn machine learning models from multiple d...
research
05/24/2023

Theoretically Principled Federated Learning for Balancing Privacy and Utility

We propose a general learning framework for the protection mechanisms th...
research
10/12/2021

Privacy-Preserving Phishing Email Detection Based on Federated Learning and LSTM

Phishing emails that appear legitimate lure people into clicking on the ...
research
06/08/2022

Gradient Obfuscation Gives a False Sense of Security in Federated Learning

Federated learning has been proposed as a privacy-preserving machine lea...
research
11/11/2020

A Novel Privacy-Preserved Recommender System Framework based on Federated Learning

Recommender System (RS) is currently an effective way to solve informati...
research
03/07/2023

A Privacy Preserving System for Movie Recommendations using Federated Learning

Recommender systems have become ubiquitous in the past years. They solve...
research
05/19/2021

A Privacy-Preserving Approach to Extraction of Personal Information through Automatic Annotation and Federated Learning

We curated WikiPII, an automatically labeled dataset composed of Wikiped...

Please sign up or login with your details

Forgot password? Click here to reset