Training Students & Researchers

Students participating in our courses and engaging in our research are exposed to a unique multidisciplinary perspective on data privacy and the interaction between technology and society more broadly. Many undergraduates and graduate students at Harvard join the project’s research after taking courses taught by project personnel. Undergraduates and law students from around the country join our summer internship and REU program. Postdocs and graduate students gain teaching and mentorship experience by serving as co-lecturers or teaching assistants in our courses, and by supervising the research of more junior researchers.

If you would like to join the project, please view our openings and contact privacytools-info@seas.harvard.edu.

Training Students & Researchers

Current & Past Students

Students join the Privacy Tools project from a variety of backgrounds, and continue their careers after the project in diverse communities.

We have hosted undergraduates as REU students as summer research interns from universities across the US, and Harvard undergraduate students joining the project both during the academic year and/or as a summer research experience. Our former undergraduate students have gone on to competitive graduate programs, industry, and government positions. 

Graduate students, both at the master’s and PhD level, may join the project as Harvard students or as researchers from other institutions. The project’s graduate students have continued in graduate school, have decided to pursue a PhD, or started a postdoctoral fellowship after graduating.

The law students on the project join from Harvard Law School and other law schools across the US. These students have gone on to work in industry positions, government positions, and postdoc fellowships.

The postdoc and research fellows on the project hold the most diverse career paths after their time on the project. Some fellows have gone into non-profit, additional postdoc fellowships, research positions, or faculty positions.

For a complete list of those currently and previously involved on the project, please visit our Postdocs & Students page.

Student Publications

Student & Postdoc Publications

2016

M. Bun and M. Zhandry, “Order revealing encryption and the hardness of private learning,” in Proceedings of the 12th Theory of Cryptography Conference (TCC 2016), Tel-Aviv, Israel, 2016. ArXiv Version BunZhandry.pdf

J. Murtagh and S. Vadhan, “The Complexity of Computing the Optimal Composition of Differential Privacy,” in Theory of Cryptography Conference (TCC 2016), 2016. ArXiv Version MurtaghVadhan.pdf

2015

M. Altman, A. Wood, D. O'Brien, S. Vadhan, and U. Gasser, “Towards a Modern Approach to Privacy-Aware Government Data Releases,” Berkeley Journal of Technology Law, Forthcoming. modernopendataprivacy.pdf

A. Askarov, S. Moore, C. Dimoulas, and S. Chong, “Cryptographic Enforcement of Language-Based Erasure,” Proceedings of the 28th IEEE Computer Security Foundations Symposium (CSF), 2015.

A. Beimel, Nissim, K., and Stemmer, U., “Learning Privately with Labeled and Unlabeled Examples,” Accepted for publication, SODA 2015, 2015. arXiv.orgAbstract 1407.2662v2.pdf

M. Bun, K. Nissim, and U. Stemmer, “Simultaneous private learning of multiple concepts,” Submitted.

M. Bun, K. Nissim, U. Stemmer, and S. Vadhan, “Differentially Private Release and Learning of Threshold Functions,” in 56th Annual IEEE Symposium on Foundations of Computer Science (FOCS 15), Berkeley, California, 2015. ArXiv VersionAbstract bunnissimstemmervadhan.pdf

M. Bun and J. Thaler, “Hardness Amplification and the Approximate Degree of Constant-Depth Circuits,” International Colloquium on Automata, Languages, and Programming (ICALP 2015) BG, 2015. ArXiv Version hardnessamplification.pdf

M. Bun, J. Ullman, and S. Vadhan, “Fingerprinting Codes and the Price of Approximate Differential Privacy,” SIAM Journal on Computing (SICOMP), Submitted. bunullmanvadhan.pdf

Y. Chen, Nissim, K., and Waggoner, B., “Fair Information Sharing for Treasure Hunting.,” in Association for the Advancement of Artificial Intelligence (AAAI), 2015.

C. Dwork, A. Smith, T. Steinke, J. Ullman, and S. Vadhan, “Robust Traceability from Trace Amounts,” in IEEE Symposium on Foundations of Computer Science (FOCS 2015), Berkeley, California, 2015.

D. O'Brien, et al., “Integrating Approaches to Privacy Across the Research Lifecycle: When is Information Purely Public?,” Social Science Research Network, 2015. SSRN Version

O. Sheffet, “Private Approximations of the 2nd-Moment Matrix Using Existing Techniques in Linear Regression,” Neural Information Processing Systems (NIPS 2015), 2015. ArXiv VersionAbstract

T. Steinke and J. Ullman, “Between Pure and Approximate Differential Privacy,” Theory and Practice of Differential Privacy (TPDP 2015), London, UK. 2015. TPDP Conference Version Between Pure and Approximate Differential Privacy.pdf

T. Steinke and J. Ullman, “Interactive Fingerprinting Codes and the Hardness of Preventing False Discovery,” JMLR: Workshop and Conference Proceedings, vol. 40, no. 201, pp. 1-41, 2015. PDF

S. Zheng, The Differential Privacy of Bayesian Inference. Bachelor's thesis, Harvard College, 2015. DASH Version

2014

Y. Chen, Sheffet, O., and Vadhan, S., “Privacy Games,” in 10th Conference on Web and Internet Economics (WINE), , Beijing, China, 2014.privacy_game_wine.pdf

A. Wood, et al., Integrating Approaches to Privacy Across the Research Lifecycle: Long-Term Longitudinal Studies. Cambridge: Harvard University, 2014. Publisher's VersionAbstractssrn-id2469848.pdf

L. Waye, “Privacy Integrated Data Stream Queries,” in Proceedings of the 2014 International Workshop on Privacy & Security in Programming (PSP '14), , New York, NY, 2014. ACM Digital Library

C. Dimoulas, Moore, S., Askarov, A., and Chong, S., “Declarative Policies for Capability Control,” in Proceedings of the 27th {IEEE} Computer Security Foundations Symposium, , Piscataway, NJ, USA, 2014.Abstractcsf14_capflow.pdf

M. Kearns, Pai, M., Roth, A., and Ullman, J., “Mechanism Design in Large Games: Incentives and Privacy,” in Proceedings of the 5th Conference on Innovations in Theoretical Computer Science, , New York, NY, USA, 2014, pp. 403–410. Publisher's Versionp403-kearns.pdf

K. Chandrasekaran, Thaler, J., Ullman, J., and Wan, A., “Faster Private Release of Marginals on Small Databases,” in Proceedings of the 5th Conference on Innovations in Theoretical Computer Science, , New York, NY, USA, 2014, pp. 387–402. Publisher's Versionp387-chandrasekaran.pdf

M. Bun, Ullman, J., and Vadhan, S., “Fingerprinting Codes and the Price of Approximate Differential Privacy,” in Proceedings of the 46th Annual ACM Symposium on Theory of Computing, , New York, NY, USA, 2014, pp. 1–10. Publisher's Versionp1-bun.pdf

T. Steinke and Ullman, J., “Interactive Fingerprinting Codes and the Hardness of Preventing False Discovery,” 2014. arXiv.orgAbstract1410.1228v1.pdf

M. Altman, O’Brien, D., and Wood, A., “Comment on the Occupational Safety and Health Administration (OSHA) Proposed Rule: Improve Tracking of Workplace Injuries and Illnesses; Extension of Comment Period”. 2014. Full Text at Regulations.govPDF version of comments

2013

S. H. Chan, Costa, T. B., and Airoldi, E. M., “Estimation of exchangeable graph models by stochastic blockmodel approximation,” in Global Conference on Signal and Information Processing (GlobalSIP), 2013 IEEE, 2013, pp. 293-296. chan_costa_airoldi_2013.pdf

L. Sweeney, Abu, A., and Winn, J., “Identifying Participants in the Personal Genome Project by Name,” Data Privacy Lab, IQSS, Harvard University. 2013. Project website PDF

S. P. Kasiviswanathan, Nissim, K., Raskhodnikova, S., and Smith, A., “Analyzing Graphs with Node Differential Privacy,” in Proceedings of the 10th Theory of Cryptography Conference on Theory of Cryptography, Berlin, Heidelberg, 2013, pp. 457–476. Publisher's Version chp3a10.10072f978-3-642-36594-2_26.pdf

A. Beimel, Nissim, K., and Stemmer, U., “Characterizing the Sample Complexity of Private Learners,” in Proceedings of the 4th Conference on Innovations in Theoretical Computer Science, New York, NY, USA, 2013, pp. 97–110. Publisher's Version p97-beimel_1.pdf

J. Ullman, “Answering n{2+o(1)} counting queries with differential privacy is hard,” in Proceedings of the 45th annual ACM symposium on Symposium on theory of computing, Palo Alto, California, USA, 2013, pp. 361-370. DOIAbstract PDF

J. Hsu, Roth, A., and Ullman, J., “Differential privacy for the analyst via private equilibrium computation,” in Proceedings of the 45th annual ACM symposium on Symposium on theory of computing, Palo Alto, California, USA, 2013, pp. 341-350. DOIAbstract PDF

G. N. Rothblum, Vadhan, S., and Wigderson, A., “Interactive proofs of proximity: delegating computation in sublinear time,” in Proceedings of the 45th annual ACM symposium on Symposium on theory of computing, Palo Alto, California, USA, 2013, pp. 793-802. DOIAbstract PDF

A. Beimel, Nissim, K., and Stemmer, U., “Characterizing the sample complexity of private learners,” in Proceedings of the 4th conference on Innovations in Theoretical Computer Science, Berkeley, California, USA, 2013, pp. 97-110. DOIAbstract PDF

A. Beimel, et al., “Private Learning and Sanitization: Pure vs. Approximate Differential Privacy,” in Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques, vol. 8096, Springer Berlin Heidelberg, 2013, pp. 363-378. Publisher's Version chp3a10.10072f978-3-642-40328-6_26.pdf

M. Bun and Thaler, J., “Dual Lower Bounds for Approximate Degree and Markov-Bernstein Inequalities,” Automata, Languages, and Programming, vol. 7965, pp. 303-314, 2013. DOIAbstract PDF

K. Chandrasekaran, Thaler, J., Ullman, J., and Wan, A., “Faster Private Release of Marginals on Small Databases,” CoRR, vol. abs/1304.3754, 2013. arXiv.orgAbstract PDF

S. P. Kasiviswanathan, Nissim, K., Raskhodnikova, S., and Smith, A., “Analyzing Graphs with Node Differential Privacy,” in Theory of Cryptography, vol. 7785, Springer Berlin Heidelberg, 2013, pp. 457-476. Springer LinkAbstract PDF

2012

J. Thaler, Ullman, J., and Vadhan, S. P., “Faster Algorithms for Privately Releasing Marginals,” in Automata, Languages, and Programming - 39th International Colloquium, ICALP 2012, Warwick, UK, 2012, Lecture Notes in Computer Science., vol. 7391. DOI:10.1007/978-3-642-31594-7_68Abstract PDF

A. Gupta, Roth, A., and Ullman, J., “Iterative Constructions and Private Data Release,” in Theory of Cryptography - 9th Theory of Cryptography Conference, TCC 2012, Taormina, Sicily, Italy, 2012, Lecture Notes in Computer Science., vol. 7194, pp. 339-356. DOI:10.1007/978-3-642-28914-9_19Abstract PDF

M. Kearns, Pai, M., Roth, A., and Ullman, J., “Private Equilibrium Release, Large Games, and No-Regret Learning,” 2012. arXiv:1207.4084Abstract PDF

S. Vadhan, et al., “Comments on Advance Notice of Proposed Rulemaking: Human Subjects Research Protections: Enhancing Protections for Research Subjects and Reducing Burden, Delay, and Ambiguity for Investigators, Docket ID number HHS-OPHS-2011-0005”. 2011. regulations.govAbstract PDF

A. Gupta, Hardt, M., Roth, A., and Ullman, J., “Privately releasing conjunctions and the statistical query barrier,” in Proceedings of the 43rd ACM Symposium on Theory of Computing, STOC 2011, San Jose, CA, USA, 2011, pp. 803-812. ACM Digital LibraryAbstract PDF

J. Ullman and Vadhan, S., “PCPs and the Hardness of Generating Synthetic Data,” in Proceedings of the 8th IACR Theory of Cryptography Conference (TCC `11), Providence, RI, 2011, Lecture Notes on Computer Science., vol. 5978, pp. 572–587. Springer LinkAbstract PDF

Student Posters

Posters of recent research done by students / researchers on the project:

2015

  1. "Testing Algorithms for Private Linear Regression" by Andreea Antuca, Haoqing Wang, James Honaker, Vishesh Karwa, Or Sheffet"
  2. "Efficient and Extensible Datalog" by Aaron Bembenek"
  3. "Visualization of Uncertainty Introduced by Differential Privacy" by Jessica Bu
  4. Jimmy Jiang
  5. "Differential Privacy and Statistical Inference" by Vishesh Karwa
  6. "Practical Differential Privacy" by Georgios Kellaris
  7. "Differentially Private CDF Evaluation and Development" by Daniel Muise
  8. "The Complexity of Computing the Optimal Composition of Differential Privacy" by Jack Murtagh
  9. "Shortest Paths and Distances with Differential Privacy" by Adam Sealfon

2014

  1. "Private Release and Learning of Thresholds" by Mark Bun
  2. "Two Ravens" by Vito D'Orazio
  3. "Privately Releasing Quantiles" by Nathan Manohar
  4. "Approximating the Optimal Composition of Differentially Private Mechanisms" by Jack Murtagh
  5. "Privacy Games" by Or Sheffet
  6. "Hardness of Preventing False Discovery" by Thomas Steinke
  7. "Learning Privately with Labeled and Unlabeled Examples" by Uri Stemmer
  8. “Privacy Integrated Data Stream Queries" by Lucas Waye
  9. "Data Tags: Legal Research & Development" Alexandra Wood
  10. "Differential Privacy of Bayesian Inference" by Joy Zheng

2013

  1. "Towards Language-­Based Anonymous Communication" by Aslan Askarov
  2. "DataTags" by Michael Bar-Sinai
  3. "Sample Complexity of Differential Privacy" by Mark Bun
  4. "Faster Private Release of Marginals on Small Databases" by Karthik Chandrasekaran
  5. "Stochastic Blockmodel Approximation of a Graph on: Theory and Consistent Estimation" by Thiago Costa
  6. "Faster Algorithms for Private Data Release" by Anna Gavrilman
  7. "Logistic Regression with Differential Privacy" by Paul Handorff
  8. "The exponential mechanism via MCMC" by Alex Makelov
  9. "Answering n2+o(1)Counting Queries with Differential Privacy is Hard" by Jon Ullman
  10. "Differentially Private Streaming Algorithms in PINQ" by Lucas Waye
  11. "Legal Approaches to Information Privacy and Data Sharing" by Alexandra Wood and Kit Walsh

Student Final Papers

Summer 2017 Student Final Papers

1. Alyssa Hu: Differentially Private Causal Inference: Confidence Intervals
2. Christian Baehr: Differentially Private Linear Regression
3. Katie Clayton: Future Directions with J-PAL Dataverse
4. Michael LoPiccolo: TransformeR: Safe R-like Variable Transformations for PSI
5. Kathryn Taylor: PSI UI/UX Experiments
6. Lancelot Wathieu: Coursened Exact Matching

Summer 2016 Student Final Papers

1. Clara Wang: PSI Tools: Building Replications Project
2. Benjamin Glass: Improving Utility of Differentially Private Confidence Intervals 
3. Fanny Chow and Nabib Ahmed: PSI (Private Data Sharing Interface) Budget Tool
4. Giovanni Malloy: Secure Remote Storage Using Oblivious RAM
5. Marcelo Novaes: System Evaluation of PSI, a Differential Privacy Prototype
6. Grace Rehaut: Causal Inference & Differential Privacy
7. Chan Kang: Exploring Composition Bound in Non-Adaptive Setting
8. Yisu "Remy" Wang: TransformeR: A DSL for Safe Variable Transformation
9. Jack Landry: Usability Testing Plan and Educational Documents for Differential Privacy

Summer 2015 Student Final Papers

  1. Andreea Antuca & Haoqing Wang: "Testing Private Regression Algorithms"
  2. Aaron Bembenek: "Datalog Engine Final Report"
  3. Jessica Bu: "Visualization of Uncertainty in Differential Privacy"
  4. Caper Gooden: "Testing Usability of Differentially Private Estimates"
  5. Ally Kaminsky: "Interactive Query Engine for Computing Differentially Private Statistics: System Design"
  6. Hyun woo Lim: "Privacy Tools for Contingency Table Analysis"
  7. Cameron Merrill: "Information Flow Control for Large Scale Data Repository Architectures"
  8. Daniel Muise: "Utility Test Development and Utility Testing for Differentially Private CDFs and PDFs"

Join the Project

The Privacy Tools project welcomes students who wish to become involved. Please refer to our call for summer interns, students, postdocs, or email Privacytools-info@seas.harvard.edu for more information.

Project Retreat, Summer 2015

Project Retreat, Summer 2014