Poisoning attacks to local differential privacy protocols for {Key-Value} data

Y Wu, X Cao, J Jia, NZ Gong - 31st USENIX Security Symposium …, 2022 - usenix.org
Local Differential Privacy (LDP) protocols enable an untrusted server to perform privacy-
preserving, federated data analytics. Various LDP protocols have been developed for …

Data poisoning attacks to local differential privacy protocols

X Cao, J Jia, NZ Gong - 30th USENIX Security Symposium (USENIX …, 2021 - usenix.org
Local Differential Privacy (LDP) protocols enable an untrusted data collector to perform
privacy-preserving data analytics. In particular, each user locally perturbs its data to …

LDPGuard: Defenses against data poisoning attacks to local differential privacy protocols

K Huang, G Ouyang, Q Ye, H Hu… - … on Knowledge and …, 2024 - ieeexplore.ieee.org
The protocols that satisfy Local Differential Privacy (LDP) enable untrusted third parties to
collect aggregate information about a population without disclosing each user's privacy. In …

Fine-grained poisoning attack to local differential privacy protocols for mean and variance estimation

X Li, N Li, W Sun, NZ Gong, H Li - 32nd USENIX Security Symposium …, 2023 - usenix.org
Although local differential privacy (LDP) protects individual users' data from inference by an
untrusted data curator, recent studies show that an attacker can launch a data poisoning …

Preventing manipulation attack in local differential privacy using verifiable randomization mechanism

F Kato, Y Cao, M Yoshikawa - Data and Applications Security and Privacy …, 2021 - Springer
Local differential privacy (LDP) has been received increasing attention as a formal privacy
definition without a trusted server. In a typical LDP protocol, the clients perturb their data …

Secure and utility-aware data collection with condensed local differential privacy

ME Gursoy, A Tamersoy, S Truex… - IEEE Transactions on …, 2019 - ieeexplore.ieee.org
Local Differential Privacy (LDP) is popularly used in practice for privacy-preserving data
collection. Although existing LDP protocols offer high utility for large user populations …

Differential aggregation against general colluding attackers

R Du, Q Ye, Y Fu, H Hu, J Li, C Fang… - 2023 IEEE 39th …, 2023 - ieeexplore.ieee.org
Local Differential Privacy (LDP) is now widely adopted in large-scale systems to collect and
analyze sensitive data while preserving users' privacy. However, almost all LDP protocols …

Cryptϵ: Crypto-assisted differential privacy on untrusted servers

A Roy Chowdhury, C Wang, X He… - Proceedings of the …, 2020 - dl.acm.org
Differential privacy (DP) is currently the de-facto standard for achieving privacy in data
analysis, which is typically implemented either in the" central" or" local" model. The local …

An adversarial approach to protocol analysis and selection in local differential privacy

ME Gursoy, L Liu, KH Chow, S Truex… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Local Differential Privacy (LDP) is a popular standard for privacy-preserving data collection.
Numerous LDP protocols have been proposed in the literature which differ in how they …

Manipulation attacks in local differential privacy

A Cheu, A Smith, J Ullman - 2021 IEEE Symposium on Security …, 2021 - ieeexplore.ieee.org
Local differential privacy is a widely studied restriction on distributed algorithms that collect
aggregates about sensitive user data, and is now deployed in several large systems. We …