Differentially private aggregation of distributed time-series with transformation and encryption

By Vibhor Rastogi, Suman Nath. 2010

611 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Federated & Distributed Learning, Privacy & Security, Signal Processing, Time-Series & Forecasting

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Federated & Distributed Learning

In Privacy & Security

In Signal Processing

In Time-Series & Forecasting

Citations in the corpus

Advances and Open Problems in Federated Learning (2019, background): “with a low ε / high privacy level) [12, 330, 181, 356, 188].”
Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learning (2020, background): “Homomorphic encryption is a cryptographic secure computation scheme that allows aggregations to be performed on encrypted data [19], [20], [21].”
Honeycrisp: large-scale differentially private aggregation without a trusted core (2019, background): “[64] does not rely on trust, but operates in a different setting where users communicate directly with each other.”
Practical Secure Aggregation for Federated Learning on User-Held Data (2016, methodology): “based on Paillier cryptosystem [15]) are very computationally expensive.”
A Comprehensive Comparison of Multiparty Secure Additions with Differential Privacy (2015, methodology): “An SMC protocol implementing such computations has high complexity [47].”
Knock Knock, Who's There? Membership Inference on Aggregate Location Data (2017, methodology): “More precisely, FPA now achieves 0.2 mean PG (vs 0.45 in the previous setting) and EFPAG provides negligible protection against membership inference (compared to 0.3 in Fig.”
A Hybrid Approach to Privacy-Preserving Federated Learning (2018, background): “Approaches for the private collection of streaming data, including [2, 8, 21, 37], aim to recover computation when one or more parties go down.”
Functional Mechanism: Regression Analysis under Differential Privacy (2012, methodology): “…[2] and Ding et al. [8] consider the publication of data cubes; Xu et al. [31] and Li et al. [18] focus on publishing histograms; McSherry and Mironov [20], Rastogi and Nath [24], and McSherry and Mahajan [19] devise methods for re-leasing counts on particular types of data, such as time series.”
Building a RAPPOR with the Unknown: Privacy-Preserving Learning of Associations and Data Dictionaries (2015, background): “Research on local differential privacy has largely been centered around finding algorithms that satisfy differential privacy properties [19, 21, 22], and improving the tradeoffs between privacy and utility [7, 14].”
Differentially-private network trace analysis (2010, background): “Appealingly, it is resilient to collusion, supports multiple interactive queries, and is also independent of any auxiliary information that an attacker might possess; such information has been shown to break anonymization [5, 26, 20, 29].”
Differentially Private Filtering (2012, background): “Compared to the previous section, for Kalman filtering it is assumed that more is publicly known about the dynamics of the processes producing the individual signals.”
Towards Statistical Queries over Distributed Private User Data (2012, methodology): “Like [45], this basic design suffers from the problem that a single malicious client can provide an answer value other than 1 or 0 in each bucket to substantially distort the”
Differential privacy based on importance weighting (2013, background): “Some of them answer unrestricted queries without publishing data (Smith 2008; McSherry and Mironov 2009; Li et al. 2010; McSherry and Mahajan 2010; Rastogi and Nath 2010).”
Fault-Tolerant Privacy-Preserving Statistics (2012, methodology): “The remainder of this paper is structured as follows: Section 2 describes the contributions of our protocol in comparison to [2,23,25].”
Real-time aggregate monitoring with differential privacy (2012, methodology): “Rastogi and Nath [12] proposed an algorithm which perturbs k Discrete Fourier Transform (DFT) coefﬁcients of the entire time series and reconstructs a released version from the Inverse DFT.”
Practical Secure Aggregation for Privacy-Preserving Machine Learning (2017, background): “Schemes based on threshold additively-homomorphic cryptosystems (e.g. the Paillier cryptosystem [35]) can handle client dropouts, but are either computationally expensive, or require additional trust assumptions.”
Differentially Private Spatial Decompositions (2011, background): “These mechanisms have been applied to various problems, such as releasing contingency tables [11], time series [17], and recommender systems [18].”
Monitoring web browsing behavior with differential privacy (2014, methodology): “Among these works two major research directions have been developed investigating the private release of numeric time series [23, 7, 11, 14, 22] and discrete series (event sequences) [16, 25] respectively.”