[KDD 2020 Best Student Paper | Research Track] TIPRDC: Task-Independent Privacy-Respecting Data Crowdsourcing Framework for Deep Learning with Anonymized Intermediate Representations

Dec 16, 2020

|

238 views

Ang Li

Adversarial Training

Details

Abstract: The success of deep learning partially benefits from the availability,of various large-scale datasets. These datasets are often crowdsourced from individual users and contain private information like,gender, age, etc. The emerging privacy concerns from users on data,sharing hinder the generation or use of crowdsourcing datasets,and lead to hunger of training data for new deep learning applications. One naïve solution is to pre-process the raw data to extract,features at the user-side, and then only the extracted features will,be sent to the data collector. Unfortunately, attackers can still exploit these extracted features to train an adversary classifier to,infer private attributes. Some prior arts leveraged game theory to,protect private attributes. However, these defenses are designed,for known primary learning tasks, the extracted features work,poorly for unknown learning tasks. To tackle the case where the,learning task may be unknown or changing, we present,TIPRDC,,,a task-independent privacy-respecting data crowdsourcing framework with anonymized intermediate representation. The goal of,this framework is to learn a feature extractor that can hide the,privacy information from the intermediate representations; while,maximally retaining the original information embedded in the raw,data for the data collector to accomplish unknown learning tasks.,We design a hybrid training method to learn the anonymized intermediate representation: (1) an adversarial training process for,hiding private information from features,; (2),maximally retain original information,using a neural-network-based mutual information,estimator. We extensively evaluate TIPRDC and compare it with existing methods using two image datasets and one text dataset. Our,results show that TIPRDC substantially outperforms other existing,methods. Our work is the first task-independent privacy-respecting,data crowdsourcing framework. Authors: Ang Li: Duke University; Yixiao Duan: Beihang University; Huanrui Yang: Duke University; Yiran Chen: Duke University; Jianlei Yang: Beihang University Paper URL: https://dl.acm.org/doi/pdf/10.1145/3394486.3403125

Category: Research Paper

Comments

loading...

Reactions (0) | Note

📝 No reactions yet

Be the first one to share your thoughts!

Reactions(0)

Note

loading...

Recommended

SREcon15 - Notes from Production Engineering

USENIX | Apr 9, 2015

SREcon15 - Case Study: Adopting SRE Principles at StackOverflow

USENIX | Apr 9, 2015

SREcon15 - Monitoring without Infrastructure @ Airbnb

USENIX | Apr 9, 2015

SREcon15 - Scaling Networks through Software

USENIX | Apr 9, 2015

SREcon15 - SRE Hiring

USENIX | Apr 9, 2015