Data Poisoning Attacks to Local Differential Privacy Protocols

11/05/2019
by   Xiaoyu Cao, et al.
0

Local Differential Privacy (LDP) protocols enable an untrusted data collector to perform privacy-preserving data analytics. In particular, each user locally perturbs his/her data to preserve privacy before sending it to the data collector, who aggregates the perturbed data to obtain statistics of interest. Over the past several years, researchers from multiple communities–such as security, database, and theoretical computer science– have proposed many LDP protocols. These studies mainly focused on improving the utility of the LDP protocols. However, the security of LDP protocols is largely unexplored. In this work, we aim to bridge this gap. We focus on LDP protocols for frequency estimation and heavy hitter identification, which are two basic data analytics tasks. Specifically, we show that an attacker can inject fake users into an LDP protocol and the fake users send carefully crafted data to the data collector such that the LDP protocol estimates high frequencies for certain items or identifies them as heavy hitters. We call our attacks data poisoning attacks. We theoretically and/or empirically show the effectiveness of our attacks. We also explore two countermeasures against our attacks. Our experimental results show that they can effectively defend against our attacks in some scenarios but have limited effectiveness in others, highlighting the needs for new defenses against our attacks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/22/2021

Poisoning Attacks to Local Differential Privacy Protocols for Key-Value Data

Local Differential Privacy (LDP) protocols enable an untrusted server to...
research
12/05/2018

Calibrate: Frequency Estimation and Heavy Hitter Identification with Local Differential Privacy via Incorporating Prior Knowledge

Estimating frequencies of certain items among a population is a basic st...
research
05/20/2019

Consistent and Accurate Frequency Oracles under Local Differential Privacy

Local Differential Privacy (LDP) protects user privacy from the data col...
research
02/09/2021

Trustless, privacy-preserving blockchain bridges

In this paper, we present a protocol for facilitating trust-less cross-c...
research
02/18/2021

Data Poisoning Attacks and Defenses to Crowdsourcing Systems

A key challenge of big data analytics is how to collect a large volume o...
research
05/15/2019

Secure and Utility-Aware Data Collection with Condensed Local Differential Privacy

Local Differential Privacy (LDP) is popularly used in practice for priva...
research
05/24/2022

Fine-grained Poisoning Attacks to Local Differential Privacy Protocols for Mean and Variance Estimation

Local differential privacy (LDP) protects individual data contributors a...

Please sign up or login with your details

Forgot password? Click here to reset