Differentially Private Distributed Frequency Estimation
نویسندگان
چکیده
In order to remain competitive, Internet companies collect and analyse user data for the purpose of improvement experiences. Frequency estimation is a widely used statistical tool, which could potentially conflict with relevant privacy regulations. Privacy preserving analytic methods based on differential have been proposed, require either large base or trusted server. Although requirements such solutions may not be problem larger companies, they unattainable smaller organizations. To address this issue, we propose distributed privacy-preserving sampling-based frequency method has high accuracy even in scenario small number users while requiring any This achieved by combining multi-party computation sampling techniques. We also provide relation between its guarantee, output accuracy, participants. Distinct from most existing methods, our achieve centralized guarantee without need established that, participants, mechanisms can produce estimates hence more opportunity growth through analysis. further an architectural model support weighted aggregation higher estimate cater varying requirements. Compared unweighted aggregation, provides accurate estimate. Extensive experiments are conducted show effectiveness proposed methods.
منابع مشابه
Locally Differentially Private Protocols for Frequency Estimation
Protocols satisfying Local Differential Privacy (LDP) enable parties to collect aggregate information about a population while protecting each user’s privacy, without relying on a trusted third party. LDP protocols (such as Google’s RAPPOR) have been deployed in real-world scenarios. In these protocols, a user encodes his private information and perturbs the encoded value locally before sending...
متن کاملDifferentially Private Password Frequency Lists
Given a dataset of user-chosen passwords, the frequency list reveals the frequency of each unique password. We present a novel mechanism for releasing perturbed password frequency lists with rigorous security, efficiency, and distortion guarantees. Specifically, our mechanism is based on a novel algorithm for sampling that enables an efficient implementation of the exponential mechanism for dif...
متن کاملDifferentially Private Distributed Online Learning
Online learning has been in the spotlight from the machine learning society for a long time. To handle massive data in Big Data era, one single learner could never efficiently finish this heavy task. Hence, in this paper, we propose a novel distributed online learning algorithm to solve the problem. Comparing to typical centralized online learner, the distributed learners optimize their own lea...
متن کاملDifferentially Private Local Electricity Markets
Privacy-preserving electricity markets have a key role in steering customers towards participation in local electricity markets by guarantying to protect their sensitive information. Moreover, these markets make it possible to statically release and share the market outputs for social good. This paper aims to design a market for local energy communities by implementing Differential Privacy (DP)...
متن کاملDifferentially private Bayesian learning on distributed data
Many applications of machine learning, for example in health care, would benefit from methods that can guarantee privacy of data subjects. Differential privacy (DP) has become established as a standard for protecting learning results, but the proposed algorithms require a single trusted party to have access to the entire data, which is a clear weakness. We consider DP Bayesian learning in a dis...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Transactions on Dependable and Secure Computing
سال: 2023
ISSN: ['1941-0018', '1545-5971', '2160-9209']
DOI: https://doi.org/10.1109/tdsc.2022.3227654