Volume
LIPIcs, Volume 218
3rd Symposium on Foundations of Responsible Computing (FORC 2022)
-
Part of:
Series:
Leibniz International Proceedings in Informatics (LIPIcs)
Conference: Symposium on Foundations of Responsible Computing (FORC)
Event
FORC 2022, June 6-8, 2022, Cambridge, MA, USAEditor
Publication Details
- published at: 2022-07-15
- Publisher: Schloss Dagstuhl – Leibniz-Zentrum für Informatik
- ISBN: 978-3-95977-226-6
- DBLP: db/conf/forc/forc2022
Access Numbers
- Detailed Access Statistics available here
-
Total Document Accesses (updated on a weekly basis):
0PDF Downloads
Documents
No documents found matching your filter selection.
Document
Complete Volume
LIPIcs, Volume 218, FORC 2022, Complete Volume
Abstract
LIPIcs, Volume 218, FORC 2022, Complete Volume
Cite as
3rd Symposium on Foundations of Responsible Computing (FORC 2022). Leibniz International Proceedings in Informatics (LIPIcs), Volume 218, pp. 1-148, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2022)
Copy BibTex To Clipboard
@Proceedings{celis:LIPIcs.FORC.2022,
title = {{LIPIcs, Volume 218, FORC 2022, Complete Volume}},
booktitle = {3rd Symposium on Foundations of Responsible Computing (FORC 2022)},
pages = {1--148},
series = {Leibniz International Proceedings in Informatics (LIPIcs)},
ISBN = {978-3-95977-226-6},
ISSN = {1868-8969},
year = {2022},
volume = {218},
editor = {Celis, L. Elisa},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.FORC.2022},
URN = {urn:nbn:de:0030-drops-165222},
doi = {10.4230/LIPIcs.FORC.2022},
annote = {Keywords: LIPIcs, Volume 218, FORC 2022, Complete Volume}
}
Document
Front Matter
Front Matter, Table of Contents, Preface, Conference Organization
Abstract
Front Matter, Table of Contents, Preface, Conference Organization
Cite as
3rd Symposium on Foundations of Responsible Computing (FORC 2022). Leibniz International Proceedings in Informatics (LIPIcs), Volume 218, pp. 0:i-0:x, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2022)
Copy BibTex To Clipboard
@InProceedings{celis:LIPIcs.FORC.2022.0,
author = {Celis, L. Elisa},
title = {{Front Matter, Table of Contents, Preface, Conference Organization}},
booktitle = {3rd Symposium on Foundations of Responsible Computing (FORC 2022)},
pages = {0:i--0:x},
series = {Leibniz International Proceedings in Informatics (LIPIcs)},
ISBN = {978-3-95977-226-6},
ISSN = {1868-8969},
year = {2022},
volume = {218},
editor = {Celis, L. Elisa},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.FORC.2022.0},
URN = {urn:nbn:de:0030-drops-165230},
doi = {10.4230/LIPIcs.FORC.2022.0},
annote = {Keywords: Front Matter, Table of Contents, Preface, Conference Organization}
}
Document
Controlling Privacy Loss in Sampling Schemes: An Analysis of Stratified and Cluster Sampling
Abstract
Sampling schemes are fundamental tools in statistics, survey design, and algorithm design. A fundamental result in differential privacy is that a differentially private mechanism run on a simple random sample of a population provides stronger privacy guarantees than the same algorithm run on the entire population. However, in practice, sampling designs are often more complex than the simple, data-independent sampling schemes that are addressed in prior work. In this work, we extend the study of privacy amplification results to more complex, data-dependent sampling schemes. We find that not only do these sampling schemes often fail to amplify privacy, they can actually result in privacy degradation. We analyze the privacy implications of the pervasive cluster sampling and stratified sampling paradigms, as well as provide some insight into the study of more general sampling designs.
Cite as
Mark Bun, Jörg Drechsler, Marco Gaboardi, Audra McMillan, and Jayshree Sarathy. Controlling Privacy Loss in Sampling Schemes: An Analysis of Stratified and Cluster Sampling. In 3rd Symposium on Foundations of Responsible Computing (FORC 2022). Leibniz International Proceedings in Informatics (LIPIcs), Volume 218, pp. 1:1-1:24, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2022)
Copy BibTex To Clipboard
@InProceedings{bun_et_al:LIPIcs.FORC.2022.1,
author = {Bun, Mark and Drechsler, J\"{o}rg and Gaboardi, Marco and McMillan, Audra and Sarathy, Jayshree},
title = {{Controlling Privacy Loss in Sampling Schemes: An Analysis of Stratified and Cluster Sampling}},
booktitle = {3rd Symposium on Foundations of Responsible Computing (FORC 2022)},
pages = {1:1--1:24},
series = {Leibniz International Proceedings in Informatics (LIPIcs)},
ISBN = {978-3-95977-226-6},
ISSN = {1868-8969},
year = {2022},
volume = {218},
editor = {Celis, L. Elisa},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.FORC.2022.1},
URN = {urn:nbn:de:0030-drops-165243},
doi = {10.4230/LIPIcs.FORC.2022.1},
annote = {Keywords: privacy, differential privacy, survey design, survey sampling}
}
Document
Leximax Approximations and Representative Cohort Selection
Abstract
Finding a representative cohort from a broad pool of candidates is a goal that arises in many contexts such as choosing governing committees and consumer panels. While there are many ways to define the degree to which a cohort represents a population, a very appealing solution concept is lexicographic maximality (leximax) which offers a natural (pareto-optimal like) interpretation that the utility of no population can be increased without decreasing the utility of a population that is already worse off. However, finding a leximax solution can be highly dependent on small variations in the utility of certain groups. In this work, we explore new notions of approximate leximax solutions with three distinct motivations: better algorithmic efficiency, exploiting significant utility improvements, and robustness to noise. Among other definitional contributions, we give a new notion of an approximate leximax that satisfies a similarly appealing semantic interpretation and relate it to algorithmically-feasible approximate leximax notions. When group utilities are linear over cohort candidates, we give an efficient polynomial-time algorithm for finding a leximax distribution over cohort candidates in the exact as well as in the approximate setting. Furthermore, we show that finding an integer solution to leximax cohort selection with linear utilities is NP-Hard.
Cite as
Monika Henzinger, Charlotte Peale, Omer Reingold, and Judy Hanwen Shen. Leximax Approximations and Representative Cohort Selection. In 3rd Symposium on Foundations of Responsible Computing (FORC 2022). Leibniz International Proceedings in Informatics (LIPIcs), Volume 218, pp. 2:1-2:22, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2022)
Copy BibTex To Clipboard
@InProceedings{henzinger_et_al:LIPIcs.FORC.2022.2,
author = {Henzinger, Monika and Peale, Charlotte and Reingold, Omer and Shen, Judy Hanwen},
title = {{Leximax Approximations and Representative Cohort Selection}},
booktitle = {3rd Symposium on Foundations of Responsible Computing (FORC 2022)},
pages = {2:1--2:22},
series = {Leibniz International Proceedings in Informatics (LIPIcs)},
ISBN = {978-3-95977-226-6},
ISSN = {1868-8969},
year = {2022},
volume = {218},
editor = {Celis, L. Elisa},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.FORC.2022.2},
URN = {urn:nbn:de:0030-drops-165258},
doi = {10.4230/LIPIcs.FORC.2022.2},
annote = {Keywords: fairness, cohort selection, leximin, maxmin}
}
Document
On Classification of Strategic Agents Who Can Both Game and Improve
Abstract
In this work, we consider classification of agents who can both game and improve. For example, people wishing to get a loan may be able to take some actions that increase their perceived credit-worthiness and others that also increase their true credit-worthiness. A decision-maker would like to define a classification rule with few false-positives (does not give out many bad loans) while yielding many true positives (giving out many good loans), which includes encouraging agents to improve to become true positives if possible. We consider two models for this problem, a general discrete model and a linear model, and prove algorithmic, learning, and hardness results for each.
For the general discrete model, we give an efficient algorithm for the problem of maximizing the number of true positives subject to no false positives, and show how to extend this to a partial-information learning setting. We also show hardness for the problem of maximizing the number of true positives subject to a nonzero bound on the number of false positives, and that this hardness holds even for a finite-point version of our linear model. We also show that maximizing the number of true positives subject to no false positive is NP-hard in our full linear model. We additionally provide an algorithm that determines whether there exists a linear classifier that classifies all agents accurately and causes all improvable agents to become qualified, and give additional results for low-dimensional data.
Cite as
Saba Ahmadi, Hedyeh Beyhaghi, Avrim Blum, and Keziah Naggita. On Classification of Strategic Agents Who Can Both Game and Improve. In 3rd Symposium on Foundations of Responsible Computing (FORC 2022). Leibniz International Proceedings in Informatics (LIPIcs), Volume 218, pp. 3:1-3:22, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2022)
Copy BibTex To Clipboard
@InProceedings{ahmadi_et_al:LIPIcs.FORC.2022.3,
author = {Ahmadi, Saba and Beyhaghi, Hedyeh and Blum, Avrim and Naggita, Keziah},
title = {{On Classification of Strategic Agents Who Can Both Game and Improve}},
booktitle = {3rd Symposium on Foundations of Responsible Computing (FORC 2022)},
pages = {3:1--3:22},
series = {Leibniz International Proceedings in Informatics (LIPIcs)},
ISBN = {978-3-95977-226-6},
ISSN = {1868-8969},
year = {2022},
volume = {218},
editor = {Celis, L. Elisa},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.FORC.2022.3},
URN = {urn:nbn:de:0030-drops-165269},
doi = {10.4230/LIPIcs.FORC.2022.3},
annote = {Keywords: Strategic Classification, Social Welfare, Learning}
}
Document
Individually-Fair Auctions for Multi-Slot Sponsored Search
Abstract
We design fair sponsored search auctions that achieve a near-optimal tradeoff between fairness and quality. Our work builds upon the model and auction design of Chawla and Jagadeesan [Chawla and Jagadeesan, 2022], who considered the special case of a single slot. We consider sponsored search settings with multiple slots and the standard model of click through rates that are multiplicatively separable into an advertiser-specific component and a slot-specific component. When similar users have similar advertiser-specific click through rates, our auctions achieve the same near-optimal tradeoff between fairness and quality as in [Chawla and Jagadeesan, 2022]. When similar users can have different advertiser-specific preferences, we show that a preference-based fairness guarantee holds. Finally, we provide a computationally efficient algorithm for computing payments for our auctions as well as those in previous work, resolving another open direction from [Chawla and Jagadeesan, 2022].
Cite as
Shuchi Chawla, Rojin Rezvan, and Nathaniel Sauerberg. Individually-Fair Auctions for Multi-Slot Sponsored Search. In 3rd Symposium on Foundations of Responsible Computing (FORC 2022). Leibniz International Proceedings in Informatics (LIPIcs), Volume 218, pp. 4:1-4:22, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2022)
Copy BibTex To Clipboard
@InProceedings{chawla_et_al:LIPIcs.FORC.2022.4,
author = {Chawla, Shuchi and Rezvan, Rojin and Sauerberg, Nathaniel},
title = {{Individually-Fair Auctions for Multi-Slot Sponsored Search}},
booktitle = {3rd Symposium on Foundations of Responsible Computing (FORC 2022)},
pages = {4:1--4:22},
series = {Leibniz International Proceedings in Informatics (LIPIcs)},
ISBN = {978-3-95977-226-6},
ISSN = {1868-8969},
year = {2022},
volume = {218},
editor = {Celis, L. Elisa},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.FORC.2022.4},
URN = {urn:nbn:de:0030-drops-165272},
doi = {10.4230/LIPIcs.FORC.2022.4},
annote = {Keywords: algorithmic fairness, advertising auctions, and individual fairness}
}
Document
Robustness Should Not Be at Odds with Accuracy
Abstract
The phenomenon of adversarial examples in deep learning models has caused substantial concern over their reliability and trustworthiness: in many instances an imperceptible perturbation can falsely flip a neural network’s prediction. Applied research in this area has mostly focused on developing novel adversarial attack strategies or building better defenses against such. It has repeatedly been pointed out that adversarial robustness may be in conflict with requirements for high accuracy. In this work, we take a more principled look at modeling the phenomenon of adversarial examples. We argue that deciding whether a model’s label change under a small perturbation is justified, should be done in compliance with the underlying data-generating process. Through a series of formal constructions, systematically analyzing the relation between standard Bayes classifiers and robust-Bayes classifiers, we make the case for adversarial robustness as a locally adaptive measure. We propose a novel way defining such a locally adaptive robust loss, show that it has a natural empirical counterpart, and develop resulting algorithmic guidance in form of data-informed adaptive robustness radius. We prove that our adaptive robust data-augmentation maintains consistency of 1-nearest neighbor classification under deterministic labels and thereby argue that robustness should not be at odds with accuracy.
Cite as
Sadia Chowdhury and Ruth Urner. Robustness Should Not Be at Odds with Accuracy. In 3rd Symposium on Foundations of Responsible Computing (FORC 2022). Leibniz International Proceedings in Informatics (LIPIcs), Volume 218, pp. 5:1-5:20, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2022)
Copy BibTex To Clipboard
@InProceedings{chowdhury_et_al:LIPIcs.FORC.2022.5,
author = {Chowdhury, Sadia and Urner, Ruth},
title = {{Robustness Should Not Be at Odds with Accuracy}},
booktitle = {3rd Symposium on Foundations of Responsible Computing (FORC 2022)},
pages = {5:1--5:20},
series = {Leibniz International Proceedings in Informatics (LIPIcs)},
ISBN = {978-3-95977-226-6},
ISSN = {1868-8969},
year = {2022},
volume = {218},
editor = {Celis, L. Elisa},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.FORC.2022.5},
URN = {urn:nbn:de:0030-drops-165280},
doi = {10.4230/LIPIcs.FORC.2022.5},
annote = {Keywords: Statistical Learning Theory, Bayes optimal classifier, adversarial perturbations, adaptive robust loss}
}
Document
Improved Generalization Guarantees in Restricted Data Models
Abstract
Differential privacy is known to protect against threats to validity incurred due to adaptive, or exploratory, data analysis - even when the analyst adversarially searches for a statistical estimate that diverges from the true value of the quantity of interest on the underlying population. The cost of this protection is the accuracy loss incurred by differential privacy. In this work, inspired by standard models in the genomics literature, we consider data models in which individuals are represented by a sequence of attributes with the property that where distant attributes are only weakly correlated. We show that, under this assumption, it is possible to "re-use" privacy budget on different portions of the data, significantly improving accuracy without increasing the risk of overfitting.
Cite as
Elbert Du and Cynthia Dwork. Improved Generalization Guarantees in Restricted Data Models. In 3rd Symposium on Foundations of Responsible Computing (FORC 2022). Leibniz International Proceedings in Informatics (LIPIcs), Volume 218, pp. 6:1-6:12, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2022)
Copy BibTex To Clipboard
@InProceedings{du_et_al:LIPIcs.FORC.2022.6,
author = {Du, Elbert and Dwork, Cynthia},
title = {{Improved Generalization Guarantees in Restricted Data Models}},
booktitle = {3rd Symposium on Foundations of Responsible Computing (FORC 2022)},
pages = {6:1--6:12},
series = {Leibniz International Proceedings in Informatics (LIPIcs)},
ISBN = {978-3-95977-226-6},
ISSN = {1868-8969},
year = {2022},
volume = {218},
editor = {Celis, L. Elisa},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.FORC.2022.6},
URN = {urn:nbn:de:0030-drops-165299},
doi = {10.4230/LIPIcs.FORC.2022.6},
annote = {Keywords: Differential Privacy, Adaptive Data Analysis, Transfer Theorem}
}
Document
Differential Secrecy for Distributed Data and Applications to Robust Differentially Secure Vector Summation
Abstract
Computing the noisy sum of real-valued vectors is an important primitive in differentially private learning and statistics. In private federated learning applications, these vectors are held by client devices, leading to a distributed summation problem. Standard Secure Multiparty Computation protocols for this problem are susceptible to poisoning attacks, where a client may have a large influence on the sum, without being detected.
In this work, we propose a poisoning-robust private summation protocol in the multiple-server setting, recently studied in PRIO [Henry Corrigan-Gibbs and Dan Boneh, 2017]. We present a protocol for vector summation that verifies that the Euclidean norm of each contribution is approximately bounded. We show that by relaxing the security constraint in SMC to a differential privacy like guarantee, one can improve over PRIO in terms of communication requirements as well as the client-side computation. Unlike SMC algorithms that inevitably cast integers to elements of a large finite field, our algorithms work over integers/reals, which may allow for additional efficiencies.
Cite as
Kunal Talwar. Differential Secrecy for Distributed Data and Applications to Robust Differentially Secure Vector Summation. In 3rd Symposium on Foundations of Responsible Computing (FORC 2022). Leibniz International Proceedings in Informatics (LIPIcs), Volume 218, pp. 7:1-7:16, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2022)
Copy BibTex To Clipboard
@InProceedings{talwar:LIPIcs.FORC.2022.7,
author = {Talwar, Kunal},
title = {{Differential Secrecy for Distributed Data and Applications to Robust Differentially Secure Vector Summation}},
booktitle = {3rd Symposium on Foundations of Responsible Computing (FORC 2022)},
pages = {7:1--7:16},
series = {Leibniz International Proceedings in Informatics (LIPIcs)},
ISBN = {978-3-95977-226-6},
ISSN = {1868-8969},
year = {2022},
volume = {218},
editor = {Celis, L. Elisa},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.FORC.2022.7},
URN = {urn:nbn:de:0030-drops-165302},
doi = {10.4230/LIPIcs.FORC.2022.7},
annote = {Keywords: Zero Knowledge, Secure Summation, Differential Privacy}
}