<html><head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class=""><p class=""><b class=""><span class="" style="font-size: 10pt; font-family: "Calibri Light", sans-serif;">The Second AAAI Workshop on Privacy-Preserving Artificial Intelligence (PPAI-21)<o:p class=""></o:p></span></b></p><p class="MsoNormal"><span class="" style="font-size: 10pt; font-family: "Calibri Light", sans-serif;"><span class="" style="font-family: Helvetica; font-size: 14px;"><span class="" style="font-size: 10pt; font-family: "Calibri Light", sans-serif;">Workshop URL<b class="">: </b></span></span><span class="" style="font-size: 10pt;"><a href="https://ppai21.github.io/" class="">https://ppai21.github.io/</a></span></span></p><p class="MsoNormal"><span class="" style="font-size: 10pt; font-family: "Calibri Light", sans-serif;">The availability of massive amounts of data, coupled with high-performance cloud computing platforms, has driven significant progress in artificial intelligence and, in particular, machine learning and optimization. It has profoundly impacted several areas, including computer vision, natural language processing, and transportation. However, the use of rich data sets also raises significant privacy concerns: They often reveal personal sensitive information that can be exploited, without the knowledge and/or consent of the involved individuals, for various purposes including monitoring, discrimination, and illegal activities. </span><span class="" style="font-family: "Calibri Light", sans-serif;"><o:p class=""></o:p></span></p><p class=""><span class="" style="font-size: 10pt; font-family: "Calibri Light", sans-serif; color: rgb(28, 30, 41);">The second AAAI <i class="">Workshop on Privacy-Preserving Artificial Intelligence</i> (PPAI-21) </span><span class="" style="font-size: 10pt; font-family: "Calibri Light", sans-serif;">held at the Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21) <span class="" style="color: rgb(28, 30, 41);">builds on the success of last year’s AAAI PPAI to provide a platform for researchers, AI practitioners, and policymakers to discuss </span>technical and societal issues and present solutions related to privacy in AI applications. The workshop will focus on both the theoretical and practical challenges related to the design of privacy-preserving AI systems and algorithms and will have strong multidisciplinary components, including soliciting contributions about policy, legal issues, and societal impact of privacy in AI. <b class=""><o:p class=""></o:p></b></span></p><p class="MsoNormal"><span class="" style="font-size: 10pt; font-family: "Calibri Light", sans-serif;">PPAI-21 will place particular emphasis on: (1) Algorithmic approaches to protect data privacy in the context of learning, optimization, and decision making that raise fundamental challenges for existing technologies; (2) Privacy challenges created by the governments and tech industry response to the Covid-19 outbreak; (3) Social issues related to tracking, tracing, and surveillance programs; and (4) Algorithms and frameworks to release privacy-preserving benchmarks and data sets.</span><span class="" style="font-family: "Calibri Light", sans-serif;"> </span></p><div class="" style="margin: 0in 0in 0.0001pt; line-height: 21px;"><b class=""><span class="" style="font-size: 10pt; line-height: 20px; font-family: "Calibri Light", sans-serif;">Topics</span></b><span class="" style="font-size: 10pt; line-height: 20px; font-family: "Calibri Light", sans-serif;"><o:p class=""></o:p></span></div><div class="" style="margin: 0in 0in 0.0001pt;"><span class="" style="font-size: 10pt; font-family: "Calibri Light", sans-serif;">The workshop organizers invite paper submissions on the following (and related) topics:</span><span class="" style="font-family: "Times New Roman"; font-size: 7pt; text-indent: -17.85pt;"> </span></div><ul type="disc" class="" style="margin-top: 0in;"><li class="MsoNormal"><span class="" style="font-size: 10pt; font-family: "Calibri Light", sans-serif;"><span class="" style="text-indent: -23.799999237060547px; font-size: 10pt;">Applications of privacy-preserving AI systems </span></span></li><li class="MsoNormal"><span class="" style="font-size: 10pt; font-family: "Calibri Light", sans-serif;"><span class="" style="text-indent: -23.799999237060547px; font-size: 10pt;">Attacks on data privacy</span></span></li><li class="MsoNormal"><span class="" style="font-size: 10pt; font-family: "Calibri Light", sans-serif;"><span class="" style="text-indent: -23.799999237060547px; font-size: 10pt;">Differential privacy: theory and applications</span></span></li><li class="MsoNormal"><span class="" style="font-size: 10pt; font-family: "Calibri Light", sans-serif;"><span class="" style="text-indent: -23.799999237060547px; font-size: 10pt;">Distributed privacy-preserving algorithms</span></span></li><li class="MsoNormal"><span class="" style="font-size: 10pt; font-family: "Calibri Light", sans-serif;"><span class="" style="text-indent: -23.799999237060547px; font-size: 10pt;">Human rights and privacy</span></span></li><li class="MsoNormal"><span class="" style="font-size: 10pt; font-family: "Calibri Light", sans-serif;"><span class="" style="text-indent: -23.799999237060547px; font-size: 10pt;">Privacy issues related to the Covid-19 outbreak</span></span></li><li class="MsoNormal"><span class="" style="font-size: 10pt; font-family: "Calibri Light", sans-serif;">Privacy policies and legal issues <o:p class=""></o:p></span></li><li class="MsoNormal"><span class="" style="font-size: 10pt; font-family: "Calibri Light", sans-serif;">Privacy preserving optimization and machine learning <o:p class=""></o:p></span></li><li class="MsoNormal"><span class="" style="font-size: 10pt; font-family: "Calibri Light", sans-serif;">Privacy preserving test cases and benchmarks <o:p class=""></o:p></span></li><li class="MsoNormal"><span class="" style="font-size: 10pt; font-family: "Calibri Light", sans-serif;">Surveillance and societal issues <o:p class=""></o:p></span></li></ul><p class=""><span class="" style="font-size: 10pt; font-family: "Calibri Light", sans-serif;">Finally, the workshop will welcome papers that describe the release of privacy-preserving <i class="">benchmarks </i>and <i class="">data sets </i>that can be used by the community to solve fundamental problems of interest, including in machine learning and optimization for health systems and urban networks, to mention but a few examples. <o:p class=""></o:p></span></p><p class="MsoNormal"><b class=""><span class="" style="font-size: 10pt; font-family: "Calibri Light", sans-serif;">Important Dates</span></b></p><ul class="MailOutline"><li class=""><span class="" style="font-family: "Calibri Light", sans-serif; font-size: 10pt; text-indent: -0.25in;">November 9, 2020 – Submission Deadline</span></li><li class=""><span class="" style="font-family: "Calibri Light", sans-serif; font-size: 10pt; text-indent: -0.25in;">November 30, 2020 – Acceptance Notification</span></li><li class=""><span class="" style="font-family: "Calibri Light", sans-serif; font-size: 10pt; text-indent: -0.25in;">February 8 and 9, 2020 – Workshop Date</span></li></ul><div class=""><br class="webkit-block-placeholder"></div><p class=""><b class=""><span class="" style="font-size: 10pt; font-family: "Calibri Light", sans-serif;">Format<br class=""></span></b><span class="" style="font-size: 10pt; font-family: "Calibri Light", sans-serif;">The workshop will be a one-day</span><span class="MsoCommentReference"><span class="" style="font-size: 8pt; font-family: Calibri, sans-serif;"> </span></span><span class="" style="font-size: 10pt; font-family: "Calibri Light", sans-serif;">and a half meeting. The first session (half day) will be dedicated to privacy challenges, particularly those risen by the Covid-19 pandemic tracing and tracking policy programs. The second, day-long, session will be dedicated to the workshop technical content about privacy-preserving AI. The workshop will include a number of (possibly parallel) technical sessions, a virtual poster session where presenters can discuss their work, with the aim of further fostering collaborations, multiple invited speakers covering crucial challenges for the field of privacy-preserving AI applications, including policy and societal impacts, a number of tutorial talks, and will conclude with a panel discussion. </span><o:p class=""></o:p></p><p class="MsoNormal" style="line-height: 12pt; vertical-align: baseline;"><b class=""><span class="" style="font-size: 10pt; font-family: "Calibri Light", sans-serif;">Attendance<o:p class=""></o:p></span></b></p><p class="MsoNormal"><span class="" style="font-size: 10pt; font-family: "Calibri Light", sans-serif;">Attendance is open to all. At least one author of each accepted submission must be present at the workshop.<br class=""><br class=""><o:p class=""></o:p></span></p><p class="MsoNormal"><b class=""><span class="" style="font-size: 10pt; font-family: "Calibri Light", sans-serif;">Submission</span></b><span class="" style="font-size: 10pt; font-family: "Calibri Light", sans-serif;"><br class="">Submission URL: <span class="apple-converted-space"> </span></span><a href="https://cmt3.research.microsoft.com/PPAI2021" class=""><span class="" style="font-size: 10pt; font-family: "Calibri Light", sans-serif;">https://cmt3.research.microsoft.com/PPAI2021</span></a><o:p class=""></o:p></p><p class=""><span class="" style="font-size: 10pt; font-family: "Calibri Light", sans-serif;">Submissions of technical papers can be up to 7 pages excluding references and appendices. Short or position papers of up to 4 pages are also welcome. All papers must be submitted in PDF format, using the AAAI-21 author kit (see the workshop website for more details).<o:p class=""></o:p></span></p><p class="MsoNormal"><b class=""><span class="" style="font-size: 10pt; font-family: "Calibri Light", sans-serif;">Invited Speakers</span></b></p><div class=""><ul class="MailOutline"><li class="">John M. Abowd (US Census Bureau)</li><li class="">Nicolas Papernot (University of Toronto)</li><li class="">Reza Shokri (National University of Singapore)</li><li class="">Steven Wu (Carnegie Mellon University)</li></ul></div><p class="MsoNormal"><b class=""><span class="" style="font-size: 10pt; font-family: "Calibri Light", sans-serif;">Workshop Chairs</span></b></p><ul class="MailOutline"><li class=""><span class="" style="font-family: "Calibri Light", sans-serif; font-size: 10pt; text-indent: -0.25in;">Ferdinando Fioretto (Syracuse University)</span></li><li class=""><span class="" style="font-family: "Calibri Light", sans-serif; font-size: 10pt; text-indent: -0.25in;">Pascal Van Hentenryck (Georgia Institute of Technology)</span></li><li class=""><span class="" style="font-family: "Calibri Light", sans-serif; font-size: 10pt; text-indent: -0.25in;">Richard W. Evans (Rice University)</span></li></ul><p class="MsoNormal"><b class=""><span class="" style="font-size: 10pt; font-family: "Calibri Light", sans-serif;">Workshop Committee</span></b></p><ul class="MailOutline"><li class=""><span class="" style="font-family: "Calibri Light", sans-serif; font-size: 10pt; text-indent: -0.25in;">Aws Albarghouthi - University of Wisconsin-Madison</span></li><li class=""><span class="" style="font-family: "Calibri Light", sans-serif; font-size: 10pt; text-indent: -0.25in;">Carsten Baum - Aarhus University</span></li><li class=""><span class="" style="font-family: "Calibri Light", sans-serif; font-size: 10pt; text-indent: -0.25in;">Aurélien Bellet - INRIA</span></li><li class=""><span class="" style="font-family: "Calibri Light", sans-serif; font-size: 10pt; text-indent: -0.25in;">Mark Bun - Boston University</span></li><li class=""><span class="" style="font-family: "Calibri Light", sans-serif; font-size: 10pt; text-indent: -0.25in;">Albert Cheu - Northeastern University</span></li><li class=""><span class="" style="font-family: "Calibri Light", sans-serif; font-size: 10pt; text-indent: -0.25in;">Graham Cormode - University of Warwick</span></li><li class=""><span class="" style="font-family: "Calibri Light", sans-serif; font-size: 10pt; text-indent: -0.25in;">Rachel Cummings - Georgia Tech</span></li><li class=""><span class="" style="font-family: "Calibri Light", sans-serif; font-size: 10pt; text-indent: -0.25in;">Xi He - University of Waterloo</span></li><li class=""><span class="" style="font-family: "Calibri Light", sans-serif; font-size: 10pt; text-indent: -0.25in;">Antti Honkela -University of Helsinki</span></li><li class=""><span class="" style="font-family: "Calibri Light", sans-serif; font-size: 10pt; text-indent: -0.25in;">Mohamed Ali Kaafar - Macquarie University and CSIRO-Data61</span></li><li class=""><span class="" style="font-family: "Calibri Light", sans-serif; font-size: 10pt; text-indent: -0.25in;">Kim Laine - Microsoft Research</span></li><li class=""><span class="" style="font-family: "Calibri Light", sans-serif; font-size: 10pt; text-indent: -0.25in;">Olga Ohrimenko - The University of Melbourne</span></li><li class=""><span class="" style="font-family: "Calibri Light", sans-serif; font-size: 10pt; text-indent: -0.25in;">Catuscia Palamidessi - Laboratoire d'informatique de l'École polytechnique</span></li><li class=""><span class="" style="font-family: "Calibri Light", sans-serif; font-size: 10pt; text-indent: -0.25in;">Marco Romanelli - INRIA</span></li><li class=""><span class="" style="font-family: "Calibri Light", sans-serif; font-size: 10pt; text-indent: -0.25in;">Reza Shokri - NUS</span></li><li class=""><span class="" style="font-family: "Calibri Light", sans-serif; font-size: 10pt; text-indent: -0.25in;">Vikrant Singhal - Northeastern University</span></li></ul><div class=""><br class=""></div></body></html>