DROPS

Document

DOI: 10.4230/LIPIcs.ITC.2024.4

Pure-DP Aggregation in the Shuffle Model: Error-Optimal and Communication-Efficient

Authors: Badih Ghazi, Ravi Kumar, and Pasin Manurangsi

Published in: LIPIcs, Volume 304, 5th Conference on Information-Theoretic Cryptography (ITC 2024)

Abstract

We obtain a new protocol for binary counting in the ε-DP_shuffle model with error O(1/ε) and expected communication Õ((log n)/ε) messages per user. Previous protocols incur either an error of O(1/ε^1.5) with O_ε(log n) messages per user (Ghazi et al., ITC 2020) or an error of O(1/ε) with O_ε(n²) messages per user (Cheu and Yan, TPDP 2022). Using the new protocol, we obtained improved ε-DP_shuffle protocols for real summation and histograms.

Cite as

Badih Ghazi, Ravi Kumar, and Pasin Manurangsi. Pure-DP Aggregation in the Shuffle Model: Error-Optimal and Communication-Efficient. In 5th Conference on Information-Theoretic Cryptography (ITC 2024). Leibniz International Proceedings in Informatics (LIPIcs), Volume 304, pp. 4:1-4:13, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)

Copy BibTex To Clipboard

@InProceedings{ghazi_et_al:LIPIcs.ITC.2024.4,
  author =	{Ghazi, Badih and Kumar, Ravi and Manurangsi, Pasin},
  title =	{{Pure-DP Aggregation in the Shuffle Model: Error-Optimal and Communication-Efficient}},
  booktitle =	{5th Conference on Information-Theoretic Cryptography (ITC 2024)},
  pages =	{4:1--4:13},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-333-1},
  ISSN =	{1868-8969},
  year =	{2024},
  volume =	{304},
  editor =	{Aggarwal, Divesh},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ITC.2024.4},
  URN =		{urn:nbn:de:0030-drops-205127},
  doi =		{10.4230/LIPIcs.ITC.2024.4},
  annote =	{Keywords: Differential Privacy, Shuffle Model, Aggregation, Pure Differential Privacy}
}

Document

DOI: 10.4230/LIPIcs.ITC.2024.6

Information-Theoretic Single-Server PIR in the Shuffle Model

Authors: Yuval Ishai, Mahimna Kelkar, Daniel Lee, and Yiping Ma

Published in: LIPIcs, Volume 304, 5th Conference on Information-Theoretic Cryptography (ITC 2024)

Abstract

We revisit the problem of private information retrieval (PIR) in the shuffle model, where queries can be made anonymously by multiple clients. We present the first single-server PIR protocol in this model that has sublinear per-client communication and information-theoretic security. Moreover, following one-time preprocessing on the server side, our protocol only requires sublinear per-client computation. Concretely, for every γ > 0, the protocol has O(n^{γ}) communication and computation costs per (stateless) client, with 1/poly(n) statistical security, assuming that a size-n database is simultaneously accessed by poly(n) clients. This should be contrasted with the recent breakthrough result of Lin, Mook, and Wichs (STOC 2023) on doubly efficient PIR in the standard model, which is (inherently) limited to computational security.

Cite as

Yuval Ishai, Mahimna Kelkar, Daniel Lee, and Yiping Ma. Information-Theoretic Single-Server PIR in the Shuffle Model. In 5th Conference on Information-Theoretic Cryptography (ITC 2024). Leibniz International Proceedings in Informatics (LIPIcs), Volume 304, pp. 6:1-6:23, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)

Copy BibTex To Clipboard

@InProceedings{ishai_et_al:LIPIcs.ITC.2024.6,
  author =	{Ishai, Yuval and Kelkar, Mahimna and Lee, Daniel and Ma, Yiping},
  title =	{{Information-Theoretic Single-Server PIR in the Shuffle Model}},
  booktitle =	{5th Conference on Information-Theoretic Cryptography (ITC 2024)},
  pages =	{6:1--6:23},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-333-1},
  ISSN =	{1868-8969},
  year =	{2024},
  volume =	{304},
  editor =	{Aggarwal, Divesh},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ITC.2024.6},
  URN =		{urn:nbn:de:0030-drops-205142},
  doi =		{10.4230/LIPIcs.ITC.2024.6},
  annote =	{Keywords: Private information retrieval, Shuffle model}
}

Document

DOI: 10.4230/LIPIcs.FSCD.2024.12

A Linear Type System for L^p-Metric Sensitivity Analysis

Authors: Victor Sannier and Patrick Baillot

Published in: LIPIcs, Volume 299, 9th International Conference on Formal Structures for Computation and Deduction (FSCD 2024)

Abstract

When working in optimisation or privacy protection, one may need to estimate the sensitivity of computer programs, i.e., the maximum multiplicative increase in the distance between two inputs and the corresponding two outputs. In particular, differential privacy is a rigorous and widely used notion of privacy that is closely related to sensitivity. Several type systems for sensitivity and differential privacy based on linear logic have been proposed in the literature, starting with the functional language Fuzz. However, they are either limited to certain metrics (L¹ and L^∞), and thus to the associated privacy mechanisms, or they rely on a complex notion of type contexts that does not interact well with operational semantics. We therefore propose a graded linear type system - inspired by Bunched Fuzz [{w}under et al., 2023] - called Plurimetric Fuzz that handles L^p vector metrics (for 1 ≤ p ≤ +∞), uses standard type contexts, gives reasonable bounds on sensitivity, and has good metatheoretical properties. We also provide a denotational semantics in terms of metric complete partial orders, and translation mappings from and to Fuzz.

Cite as

Victor Sannier and Patrick Baillot. A Linear Type System for L^p-Metric Sensitivity Analysis. In 9th International Conference on Formal Structures for Computation and Deduction (FSCD 2024). Leibniz International Proceedings in Informatics (LIPIcs), Volume 299, pp. 12:1-12:22, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)

Copy BibTex To Clipboard

@InProceedings{sannier_et_al:LIPIcs.FSCD.2024.12,
  author =	{Sannier, Victor and Baillot, Patrick},
  title =	{{A Linear Type System for L^p-Metric Sensitivity Analysis}},
  booktitle =	{9th International Conference on Formal Structures for Computation and Deduction (FSCD 2024)},
  pages =	{12:1--12:22},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-323-2},
  ISSN =	{1868-8969},
  year =	{2024},
  volume =	{299},
  editor =	{Rehof, Jakob},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.FSCD.2024.12},
  URN =		{urn:nbn:de:0030-drops-203412},
  doi =		{10.4230/LIPIcs.FSCD.2024.12},
  annote =	{Keywords: type system, linear logic, sensitivity, vector metrics, differential privacy, lambda-calculus, functional programming, denotational semantics}
}

Document

Track A: Algorithms, Complexity and Games

DOI: 10.4230/LIPIcs.ICALP.2024.27

The Discrepancy of Shortest Paths

Authors: Greg Bodwin, Chengyuan Deng, Jie Gao, Gary Hoppenworth, Jalaj Upadhyay, and Chen Wang

Published in: LIPIcs, Volume 297, 51st International Colloquium on Automata, Languages, and Programming (ICALP 2024)

Abstract

The hereditary discrepancy of a set system is a quantitative measure of the pseudorandom properties of the system. Roughly speaking, hereditary discrepancy measures how well one can 2-color the elements of the system so that each set contains approximately the same number of elements of each color. Hereditary discrepancy has numerous applications in computational geometry, communication complexity and derandomization. More recently, the hereditary discrepancy of the set system of shortest paths has found applications in differential privacy [Chen et al. SODA 23]. The contribution of this paper is to improve the upper and lower bounds on the hereditary discrepancy of set systems of unique shortest paths in graphs. In particular, we show that any system of unique shortest paths in an undirected weighted graph has hereditary discrepancy O(n^{1/4}), and we construct lower bound examples demonstrating that this bound is tight up to polylog n factors. Our lower bounds hold even for planar graphs and bipartite graphs, and improve a previous lower bound of Ω(n^{1/6}) obtained by applying the trace bound of Chazelle and Lvov [SoCG'00] to a classical point-line system of Erdős. As applications, we improve the lower bound on the additive error for differentially-private all pairs shortest distances from Ω(n^{1/6}) [Chen et al. SODA 23] to Ω̃(n^{1/4}), and we improve the lower bound on additive error for the differentially-private all sets range queries problem to Ω̃(n^{1/4}), which is tight up to polylog n factors [Deng et al. WADS 23].

Cite as

Greg Bodwin, Chengyuan Deng, Jie Gao, Gary Hoppenworth, Jalaj Upadhyay, and Chen Wang. The Discrepancy of Shortest Paths. In 51st International Colloquium on Automata, Languages, and Programming (ICALP 2024). Leibniz International Proceedings in Informatics (LIPIcs), Volume 297, pp. 27:1-27:20, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)

Copy BibTex To Clipboard

@InProceedings{bodwin_et_al:LIPIcs.ICALP.2024.27,
  author =	{Bodwin, Greg and Deng, Chengyuan and Gao, Jie and Hoppenworth, Gary and Upadhyay, Jalaj and Wang, Chen},
  title =	{{The Discrepancy of Shortest Paths}},
  booktitle =	{51st International Colloquium on Automata, Languages, and Programming (ICALP 2024)},
  pages =	{27:1--27:20},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-322-5},
  ISSN =	{1868-8969},
  year =	{2024},
  volume =	{297},
  editor =	{Bringmann, Karl and Grohe, Martin and Puppis, Gabriele and Svensson, Ola},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ICALP.2024.27},
  URN =		{urn:nbn:de:0030-drops-201705},
  doi =		{10.4230/LIPIcs.ICALP.2024.27},
  annote =	{Keywords: Discrepancy, hereditary discrepancy, shortest paths, differential privacy}
}

Document

DOI: 10.4230/LIPIcs.ITP.2021.10

Verified Progress Tracking for Timely Dataflow

Authors: Matthias Brun, Sára Decova, Andrea Lattuada, and Dmitriy Traytel

Published in: LIPIcs, Volume 193, 12th International Conference on Interactive Theorem Proving (ITP 2021)

Abstract

Large-scale stream processing systems often follow the dataflow paradigm, which enforces a program structure that exposes a high degree of parallelism. The Timely Dataflow distributed system supports expressive cyclic dataflows for which it offers low-latency data- and pipeline-parallel stream processing. To achieve high expressiveness and performance, Timely Dataflow uses an intricate distributed protocol for tracking the computation’s progress. We modeled the progress tracking protocol as a combination of two independent transition systems in the Isabelle/HOL proof assistant. We specified and verified the safety of the two components and of the combined protocol. To this end, we identified abstract assumptions on dataflow programs that are sufficient for safety and were not previously formalized.

Cite as

Matthias Brun, Sára Decova, Andrea Lattuada, and Dmitriy Traytel. Verified Progress Tracking for Timely Dataflow. In 12th International Conference on Interactive Theorem Proving (ITP 2021). Leibniz International Proceedings in Informatics (LIPIcs), Volume 193, pp. 10:1-10:20, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2021)

Copy BibTex To Clipboard

@InProceedings{brun_et_al:LIPIcs.ITP.2021.10,
  author =	{Brun, Matthias and Decova, S\'{a}ra and Lattuada, Andrea and Traytel, Dmitriy},
  title =	{{Verified Progress Tracking for Timely Dataflow}},
  booktitle =	{12th International Conference on Interactive Theorem Proving (ITP 2021)},
  pages =	{10:1--10:20},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-188-7},
  ISSN =	{1868-8969},
  year =	{2021},
  volume =	{193},
  editor =	{Cohen, Liron and Kaliszyk, Cezary},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ITP.2021.10},
  URN =		{urn:nbn:de:0030-drops-139057},
  doi =		{10.4230/LIPIcs.ITP.2021.10},
  annote =	{Keywords: safety, distributed systems, timely dataflow, Isabelle/HOL}
}

Document

DOI: 10.4230/DagSemProc.09511.6

Differentially Private Combinatorial Optimization

Authors: Kunal Talwar, Anupam Gupta, Katrina Ligett, Frank McSherry, and Aaron Roth

Published in: Dagstuhl Seminar Proceedings, Volume 9511, Parameterized complexity and approximation algorithms (2010)

Abstract

Consider the following problem: given a metric space, some of whose points are ``clients,'' select a set of at most $k$ facility locations to minimize the average distance from the clients to their nearest facility. This is just the well-studied $k$-median problem, for which many approximation algorithms and hardness results are known. Note that the objective function encourages opening facilities in areas where there are many clients, and given a solution, it is often possible to get a good idea of where the clients are located. This raises the following quandary: what if the locations of the clients are sensitive information that we would like to keep private? emph{Is it even possible to design good algorithms for this problem that preserve the privacy of the clients?} In this paper, we initiate a systematic study of algorithms for discrete optimization problems in the framework of differential privacy (which formalizes the idea of protecting the privacy of individual input elements). We show that many such problems indeed have good approximation algorithms that preserve differential privacy; this is even in cases where it is impossible to preserve cryptographic definitions of privacy while computing any non-trivial approximation to even the emph{value} of an optimal solution, let alone the entire solution. Apart from the $k$-median problem, we consider the problems of vertex and set cover, min-cut, facility location, and Steiner tree, and give approximation algorithms and lower bounds for these problems. We also consider the recently introduced submodular maximization problem, ``Combinatorial Public Projects'' (CPP), shown by Papadimitriou et al. cite{PSS08} to be inapproximable to subpolynomial multiplicative factors by any efficient and emph{truthful} algorithm. We give a differentially private (and hence approximately truthful) algorithm that achieves a logarithmic additive approximation. Joint work with Anupam Gupta, Katrina Ligett, Frank McSherry and Aaron Roth.

Cite as

Kunal Talwar, Anupam Gupta, Katrina Ligett, Frank McSherry, and Aaron Roth. Differentially Private Combinatorial Optimization. In Parameterized complexity and approximation algorithms. Dagstuhl Seminar Proceedings, Volume 9511, pp. 1-31, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2010)

Copy BibTex To Clipboard

@InProceedings{talwar_et_al:DagSemProc.09511.6,
  author =	{Talwar, Kunal and Gupta, Anupam and Ligett, Katrina and McSherry, Frank and Roth, Aaron},
  title =	{{Differentially Private Combinatorial Optimization}},
  booktitle =	{Parameterized complexity and approximation algorithms},
  pages =	{1--31},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2010},
  volume =	{9511},
  editor =	{Erik D. Demaine and MohammadTaghi Hajiaghayi and D\'{a}niel Marx},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.09511.6},
  URN =		{urn:nbn:de:0030-drops-24986},
  doi =		{10.4230/DagSemProc.09511.6},
  annote =	{Keywords: Differential Privacy, Approximation Algorithms}
}

6 Search Results for "McSherry, Frank"

Pure-DP Aggregation in the Shuffle Model: Error-Optimal and Communication-Efficient

Abstract

Cite as

Information-Theoretic Single-Server PIR in the Shuffle Model

Abstract

Cite as

A Linear Type System for L^p-Metric Sensitivity Analysis

Abstract

Cite as

The Discrepancy of Shortest Paths

Abstract

Cite as

Verified Progress Tracking for Timely Dataflow

Abstract

Cite as

Differentially Private Combinatorial Optimization

Abstract

Cite as