My research is in computer security and privacy. More specifically, I am interested in designing inference algorithms to quantify information leakage of a system about its sensitive inputs. I also design privacy-preserving mechanisms to mitigate the risks of such inference attacks. My current focus is on machine learning and data privacy.
I have multiple open positions for postdocs, PhD students, and interns.
Reza Shokri, Marco Stronati, Congzheng Song, and Vitaly Shmatikov
➙ Membership Inference Attacks against Machine Learning Models ➙ [code] ➙ [talk]
In IEEE Symposium on Security and Privacy (S&P) -- Oakland, 2017.
Vincent Bindschaedler, Reza Shokri, and Carl Gunter
➙ Plausible Deniability for Privacy-Preserving Data Synthesis ➙ [code]
In the Proceedings of the VLDB Endowment International Conference on Very Large Data Bases (PVLDB), 2017.
Vincent Bindschaedler and Reza Shokri.
➙ Synthesizing Plausible Privacy-Preserving Location Traces ➙ [code] ➙ [talk by V. Bindschaedler]
In IEEE Symposium on Security and Privacy (S&P) -- Oakland, 2016.
Reza Shokri, George Theodorakopoulos, and Carmela Troncoso
➙ Privacy Games along Location Traces: A Game-Theoretic Framework for Optimizing Location Privacy
In the ACM Transactions on Privacy and Security (TOPS), 2016.
Reza Shokri and Vitaly Shmatikov.
➙ Privacy-Preserving Deep Learning ➙ [code]
In ACM Conference on Computer and Communications Security (CCS), 2015.
(Invited to) Annual Allerton Conference on Communication, Control, and Computing (Allerton) 2015
Media: MIT Technology Review
➙ Privacy Games: Optimal User-Centric Data Obfuscation
In Privacy Enhancing Technologies Symposium (PETS), 2015
Igor Bilogrevic, Kevin Huguenin, Stephan Mihaila, Reza Shokri, and Jean-Pierre Hubaux.
➙ Predicting Users' Motivations behind Location Check-Ins and Utility Implications of Privacy Protection Mechanisms
In Network and Distributed System Security (NDSS) Symposium, 2015.
Reza Shokri, George Theodorakopoulos, Panos Papadimitratos, Ehsan Kazemi, and Jean-Pierre Hubaux.
➙ Hiding in the Mobile Crowd: Location Privacy through Collaboration
In IEEE Transactions on Dependable and Secure Computing (TDSC), 2014.
Reza Shokri, George Theodorakopoulos, Carmela Troncoso, Jean-Pierre Hubaux, and Jean-Yves Le Boudec.
➙ Protecting Location Privacy: Optimal Strategy against Localization Attacks ➙ [code]
In the 19th ACM Conference on Computer and Communications Security (CCS), 2012.
Reza Shokri, George Theodorakopoulos, Jean-Yves Le Boudec, and Jean-Pierre Hubaux.
➙ Quantifying Location Privacy ➙ [code]
In IEEE Symposium on Security and Privacy (S&P) -- Oakland, 2011.
Award: Recognized as the runner-up for the Outstanding Research in Privacy Enhancing Technologies 2012.
CS4257: Algorithmic Foundations of Privacy
CS6101: Privacy and Security in Machine Learning
➙ One open position for a postdoc. Candidates need to have strong analytical skills, with background in statistics, probabilistic models, and machine learning. The project is about designing privacy-preserving generative models for data synthesis, and analyzing privacy in machine learning. The preferred starting time is August 2018, and the duration is one year (with the possibility of extending for the second year).
➙ Two open positions for PhD students. Candidates need to get admission from the computer science department.
➙ Multiple open positions for (senior undergraduate, and graduate students as) interns and research assistants. Students need to have strong analytical skills. The duration of the research projects is at least 6 months.
If you are interested, please fill in this form.