Efficient Defenses Against Output Poisoning Attacks on Local Differential Privacy
- 15 August 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 18 (15566013) , 5506-5521
Abstract
Local differential privacy (LDP) is a promising technique to realize privacy-preserving data aggregation without a trusted aggregator. Normally, an LDP protocol requires each user to locally perturb his raw data and submit the perturbed data to the aggregator. Consequently, LDP is vulnerable to output poisoning attacks. Malicious users can skip the perturbation and submit carefully crafted data to the aggregator, altering the data aggregation results. Existing verifiable LDP protocols, which can verify the perturbation process and prevent output poisoning attacks, usually incur significant computation and communication costs, due to the use of zero-knowledge proofs. In this paper, we analyze the attacks on two classic LDP protocols for frequency estimation, namely GRR and OUE, and propose two verifiable LDP protocols. The proposed protocols are based on an interactive framework, where the user and the aggregator complete the perturbation together. By providing some additional information, which reveals nothing about the raw data but helps the verification, the user can convince the aggregator that he is incapable of launching an output poisoning attack. Simulation results demonstrate that the proposed protocols have good defensive performance and outperform existing approaches in terms of efficiency.Keywords
Funding Information
- National Natural Science Foundation of China (62272039)
- Natural Science Foundation of Beijing Municipality (M21035)
This publication has 33 references indexed in Scilit:
- Subpopulation Data Poisoning Attacks2021
- Local Differential Privacy for Deep LearningIEEE Internet of Things Journal, 2019
- PrivKV: Key-Value Data Collection with Local Differential Privacy2019
- Collecting and Analyzing Multidimensional Data with Local Differential Privacy2019
- Locally Differentially Private Frequent Itemset Mining2018
- Bulletproofs: Short Proofs for Confidential Transactions and More2018
- Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning2018
- $\textsf{LoPub}$ : High-Dimensional Crowdsourced Data Publication With Local Differential PrivacyIEEE Transactions on Information Forensics and Security, 2018
- RAPPOR2014
- What Can We Learn Privately?SIAM Journal on Computing, 2011