Filters








10,271 Hits in 5.1 sec

Online Learning via the Differential Privacy Lens [article]

Jacob Abernethy, Young Hun Jung, Chansoo Lee, Audra McMillan, Ambuj Tewari
2019 arXiv   pre-print
In this paper, we use differential privacy as a lens to examine online learning in both full and partial information settings.  ...  We show that tools from the differential privacy literature can yield regret bounds for many interesting online learning problems including online convex optimization and online linear optimization.  ...  Acknowledgments Part of this work was done while AM was visiting the Simons Institute for the Theory of Computing.  ... 
arXiv:1711.10019v4 fatcat:plfs7qawrzfcvhnauy2beyt56u

Anon what what?

Stacy Black, Rezvan Joshaghani, Dhanush kumar Ratakonda, Hoda Mehrpouyan, Jerry Alan Fails
2019 Proceedings of the Interaction Design and Children on ZZZ - IDC '19  
learning [4, 5, 9] would be a useful approach to teach children how to protect themselves online.  ...  The participatory design theater was viewed as a brief case-study and looked at with a qualitative lens.  ... 
doi:10.1145/3311927.3325324 dblp:conf/acmidc/BlackJRMF19 fatcat:h2xfiep26rcutkcvbmooejb5fe

Utility/Privacy Trade-off through the lens of Optimal Transport [article]

Etienne Boursier, Vianney Perchet
2020 arXiv   pre-print
We apply these techniques to preserve some privacy in online repeated auctions.  ...  on the private knowledge).  ...  Differential privacy is the most widely used private learning framework (Dwork, 2011; Dwork et al., 2006; Reed and Pierce, 2010) and ensures that the output of an algorithm does not significantly depend  ... 
arXiv:1905.11148v3 fatcat:lhg7qa2i65dn5gvd62feifvhdi

Introduction and Overview [chapter]

Bart P. Knijnenburg, Xinru Page, Pamela Wisniewski, Heather Richter Lipford, Nicholas Proferes, Jennifer Romano
2022 Modern Socio-Technical Perspectives on Privacy  
AbstractThis chapter introduces the book Modern Socio-Technical Perspectives on Privacy.  ...  The book informs academic researchers and industry professionals about the socio-technical privacy challenges related to modern networked technologies.  ...  It acknowledges an important deficiency of existing policies: they regulate neither the data collected by health monitoring and fitness sensors nor the data that is shared via social media, online communities  ... 
doi:10.1007/978-3-030-82786-1_1 fatcat:n46lj3hrjfejdpvrr5kqhviilu

Mobile Applications for Privacy-Preserving Digital Contact Tracing

Christos Laoudias, Steffen Meyer, Philippos Isaia, Thomas Windisch, Justus Benzler, Maximilian Lenkeit
2022 Zenodo  
Our presentation will be delivered through the lens of 2 country-wide MCTA, namely the Corona-Warn-App (CWA) and the CovTracer-Exposure Notification (CovTracer-EN) app deployed in Germany and Cyprus, respectively  ...  Presentation slides of the advanced seminar "Mobile Applications for Privacy-Preserving Digital Contact Tracing" presented at the 23rd IEEE Intl. Conference on Mobile Data Management (MDM 2022).  ...  generally received their test results via the app within 24 hours.  ... 
doi:10.5281/zenodo.6622627 fatcat:fkcwwnz4ebg6jhjpkpae77n7su

Privacy Intelligence: A Survey on Image Privacy in Online Social Networks [article]

Chi Liu, Tianqing Zhu, Jun Zhang, Wanlei Zhou
2021 arXiv   pre-print
Image sharing on online social networks (OSNs) has become an indispensable part of daily social activities, but it has also led to an increased risk of privacy invasion.  ...  The resulting analysis describes an intelligent privacy firewall for closed-loop privacy management. We also discuss the challenges and future directions in this area.  ...  ) by contesting with a discriminative model via adversarial learning [115] .  ... 
arXiv:2008.12199v2 fatcat:vxv6rsnyavesjiw2bbnc4jzsiy

Signal Processing and Machine Learning with Differential Privacy: Algorithms and Challenges for Continuous Data

Anand D. Sarwate, Kamalika Chaudhuri
2013 IEEE Signal Processing Magazine  
We hope that interested readers will investigate the wide range of topics that have been studied through the lens of differential privacy.  ...  , but to learn the true hypothesis with differential privacy we must choose n as a function of the data distribution.  ... 
doi:10.1109/msp.2013.2259911 pmid:24737929 pmcid:PMC3984544 fatcat:37k4byrgbbgdxcqq76vpv5idzy

Intention to disclose personal information via mobile applications: A privacy calculus perspective

Tien Wang, Trong Danh Duong, Charlie C. Chen
2016 International Journal of Information Management  
the calculus lens.  ...  the calculus lens.  ...  About 54% of the mobile users in the study chose not to install certain apps after learning potential risks of information disclosure via such apps.  ... 
doi:10.1016/j.ijinfomgt.2016.03.003 fatcat:xkpttaqegbbi7lbrcxdra3rziu

Designing for the Privacy Commons [chapter]

Darakhshan J. Mir
2021 Governing Privacy in Knowledge Commons  
This chapter frames privacy enforcement processes through the lens of governance and situated design of sociotechnical systems.  ...  It considers the challenges in formulating and designing privacy as commons (as per the Governing Knowledge Commons framework (Sanfilippo, Frischmann, and Strandburg 2018)) when privacy ultimately gets  ...  online activity held by the online advertisers who place ads on the websites they visit will remain private and secure.  ... 
doi:10.1017/9781108749978.011 fatcat:cq2zldp5rfa3hnuassmmjig5ka

Editorial

Vincent Y. F. Tan, Yao Xie
2021 IEEE Journal on Selected Areas in Information Theory  
Along similar lines, the special issue includes a set of papers in active learning and classification with abstention, and also to various aspects of reinforcement learning through the lens of coding and  ...  In recent years, sequential methods have become hugely popular in domains such as reinforcement learning, multi-armed bandits, online convex optimization, and active learning.  ...  We would like to thank the authors for submitting their best work to this special issue and the reviewers for their thorough and meticulous reviews to uphold the quality of the papers.  ... 
doi:10.1109/jsait.2021.3086220 fatcat:ndy37h4e4fg6xbiu4fzv6cjxme

Differentially Private Bayesian Optimization [article]

Matt J. Kusner, Jacob R. Gardner, Roman Garnett, Kilian Q. Weinberger
2015 arXiv   pre-print
Leveraging the strong theoretical guarantees of differential privacy and known Bayesian optimization convergence bounds, we prove that under a GP assumption these private quantities are also near-optimal  ...  The success of machine learning has led practitioners in diverse real-world settings to learn classifiers for practical problems.  ...  Differential privacy has been shown to be achievable in online and interactive kernel learning settings (Jain et al., 2012; Smith & Thakurta, 2013b; Jain & Thakurta, 2013; Mishra & Thakurta, 2014) .  ... 
arXiv:1501.04080v2 fatcat:h2hg3i3ajrghbiksnwa7erc2ty

Trustworthy AI Inference Systems: An Industry Research View [article]

Rosario Cammarota, Matthias Schunter, Anand Rajan, Fabian Boemer, Ágnes Kiss, Amos Treiber, Christian Weinert, Thomas Schneider, Emmanuel Stapf, Ahmad-Reza Sadeghi, Daniel Demmler, Huili Chen (+16 others)
2020 arXiv   pre-print
Regarding the protection mechanisms, we survey the security and privacy building blocks instrumental in designing, building, deploying, and operating private AI inference systems.  ...  Additionally, such systems should also use Privacy-Enhancing Technologies (PETs) to protect customers' data at any time.  ...  In machine learning, differential privacy is provided by adding noise to during the training process.  ... 
arXiv:2008.04449v1 fatcat:2loel5z6wnhabolegry4gff7oq

Putting Privacy into Perspective – Comparing Technical, Legal, and Users' View of Information Sensitivity

Eva-Maria Schomakers, Chantal Lidynia, Dirk Müllmann, Roman Matzutt, Klaus Wehrle, Indra Spiecker genannt Döhmann, Martina Ziefle
2021 Informatik 2020 : Fachtagung vom 28. September - 2. Oktober 2020 / Ralf H. Reussner  
Our key findings still suggest the GDPR adequately protecting users' privacy but for small adjustments.  ...  However, the technological advances and increased user participation generate novel challenges for users' privacy.  ...  The responsibility for the content of this publication lies with the authors.  ... 
doi:10.18154/rwth-2021-01253 fatcat:qygpkmntb5ajlmnv4tanlcwrma

Artificial intelligence in schools: Towards a democratic future

Sandra Leaton Gray
2020 London Review of Education  
This in turn is used to highlight data privacy rights issues for children and young people, as defined by the 2018 General Data Protection Regulations (GDPR).  ...  The article concludes that achieving a balance between fairness, individual pedagogic rights ( Bernstein, 2000 ), data privacy rights and effective use of data is a difficult challenge, and one not easily  ...  privacy rights organization.  ... 
doi:10.14324/lre.18.2.02 fatcat:2p42or3zmreyvoqt57vvk2dgwa

The Algorithmic Foundations of Differential Privacy

Cynthia Dwork, Aaron Roth
2013 Foundations and Trends® in Theoretical Computer Science  
corrections on early drafts of this book, including Vitaly Feldman, Justin Hsu, Katrina Ligett, Dong Lin, David Parkes, Ryan Rogers, Guy Rothblum, Ian Schmutte, Jon Ullman, Salil Vadhan, Zhiwei Steven Wu, and the  ...  The differential privacy lens An online etymological dictionary describes the original 18th century meaning of the term of the word "statistics" as "science dealing with data about the condition of a state  ...  This eventulaly lead, via more general queries [31, 6] , to differential privacy.  ... 
doi:10.1561/0400000042 fatcat:jk3mb6ltcfeqzeyvpyznpohuja
« Previous Showing results 1 — 15 out of 10,271 results