Y. Chen, Nissim, K., and Waggoner, B., “Fair Information Sharing for Treasure Hunting.,” in Association for the Advancement of Artificial Intelligence (AAAI), , 2015.
A. Beimel, Nissim, K., and Stemmer, U., “Learning Privately with Labeled and Unlabeled Examples,” Accepted for publication, SODA 2015, , 2015. arXiv.orgAbstract
A private learner is an algorithm that given a sample of labeled individual examples outputs a generalizing hypothesis while preserving the privacy of each individual. In 2008, Kasiviswanathan et al. (FOCS 2008) gave a generic construction of private learners, in which the sample complexity is (generally) higher than what is needed for non-private learners. This gap in the sample complexity was then further studied in several followup papers, showing that (at least in some cases) this gap is unavoidable. Moreover, those papers considered ways to overcome the gap, by relaxing either the privacy or the learning guarantees of the learner. We suggest an alternative approach, inspired by the (non-private) models of semi-supervised learning and active-learning, where the focus is on the sample complexity of labeled examples whereas unlabeled examples are of a significantly lower cost. We consider private semi-supervised learners that operate on a random sample, where only a (hopefully small) portion of this sample is labeled. The learners have no control over which of the sample elements are labeled. Our main result is that the labeled sample complexity of private learners is characterized by the VC dimension. We present two generic constructions of private semi-supervised learners. The first construction is of learners where the labeled sample complexity is proportional to the VC dimension of the concept class, however, the unlabeled sample complexity of the algorithm is as big as the representation length of domain elements. Our second construction presents a new technique for decreasing the labeled sample complexity of a given private learner, while only slightly increasing its unlabeled sample complexity. In addition, we show that in some settings the labeled sample complexity does not depend on the privacy parameters of the learner.
C. Dimoulas, Moore, S., Askarov, A., and Chong, S., “Declarative Policies for Capability Control,” in Computer Security Foundations Symposium (CSF), , 2014. csf14_capflow.pdf
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
R. Bassily, Smith, A., and Thakurta, A., “

Private Empirical Risk Minimization, Revisited

,” in ICML 2014 Workshop on Learning, Security and Privacy, , Beijing, China, 2014. Publisher's VersionAbstract
In this paper, we initiate a systematic investigation of differentially private algorithms for convex empirical risk minimization. Various instantiations of this problem have been studied before. We provide new algorithms and matching lower bounds for private ERM assuming only that each data point's contribution to the loss function is Lipschitz bounded and that the domain of optimization is bounded. We provide a separate set of algorithms and matching lower bounds for the setting in which the loss functions are known to also be strongly convex.  Our algorithms run in polynomial time, and in some cases even match the optimal non-private running time (as measured by oracle complexity). We give separate algorithms (and lower bounds) for (ϵ,0)- and (ϵ,δ)-differential privacy; perhaps surprisingly, the techniques used for designing optimal algorithms in the two cases are completely different. Our lower bounds apply even to very simple, smooth function families, such as linear and quadratic functions. This implies that algorithms from previous work can be used to obtain optimal error rates, under the additional assumption that the contributions of each data point to the loss function is smooth. We show that simple approaches to smoothing arbitrary loss functions (in order to apply previous techniques) do not yield optimal error rates. In particular, optimal algorithms were not previously known for problems such as training support vector machines and the high-dimensional median.
A. Wood, et al.,

Integrating Approaches to Privacy Across the Research Lifecycle: Long-Term Longitudinal Studies

. Cambridge: Harvard University, 2014. Publisher's VersionAbstract
On September 24-25, 2013, the Privacy Tools for Sharing Research Data project at Harvard University held a workshop titled "Integrating Approaches to Privacy across the Research Data Lifecycle." Over forty leading experts in computer science, statistics, law, policy, and social science research convened to discuss the state of the art in data privacy research. The resulting conversations centered on the emerging tools and approaches from the participants’ various disciplines and how they should be integrated in the context of real-world use cases that involve the management of confidential research data.This workshop report, the first in a series, provides an overview of the long-term longitudinal study use case. Long-term longitudinal studies collect, at multiple points over a long period of time, highly-specific and often sensitive data describing the health, socioeconomic, or behavioral characteristics of human subjects. The value of such studies lies in part in their ability to link a set of behaviors and changes to each individual, but these factors tend to make the combination of observable characteristics associated with each subject unique and potentially identifiable.Using the research information lifecycle as a framework, this report discusses the defining features of long-term longitudinal studies and the associated challenges for researchers tasked with collecting and analyzing such data while protecting the privacy of human subjects. It also describes the disclosure risks and common legal and technical approaches currently used to manage confidentiality in longitudinal data. Finally, it identifies urgent problems and areas for future research to advance the integration of various methods for preserving confidentiality in research data.
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.Abstract
In capability-safe languages, components can access a resource only if they possess a capability for that resource. As a result, a programmer can prevent an untrusted component from accessing a sensitive resource by ensuring that the component never acquires the corresponding capability. In order to reason about which components may use a sensitive resource it is necessary to reason about how capabilities propagate through a system. This may be difficult, or, in the case of dynamically composed code, impossible to do before running the system. To counter this situation, we propose extensions to capability-safe languages that restrict the use of capabilities according to declarative policies. We introduce two independently useful semantic security policies to regulate capabilities and describe language-based mechanisms that enforce them. Access control policies restrict which components may use a capability and are enforced using higher-order contracts. Integrity policies restrict which components may influence (directly or indirectly) the use of a capability and are enforced using an information-flow type system. Finally, we describe how programmers can dynamically and soundly combine components that enforce access control or integrity policies with components that enforce different policies or even no policy at all.
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 Version p403-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 Version p387-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 Version p1-bun.pdf
K. Nissim, Vadhan, S., and Xiao, D., “

Redrawing the Boundaries on Purchasing Data from Privacy-sensitive Individuals

,” in Proceedings of the 5th Conference on Innovations in Theoretical Computer Science, , New York, NY, USA, 2014, pp. 411–422. Publisher's Version p411-nissim.pdf
T. Steinke and Ullman, J., “Interactive Fingerprinting Codes and the Hardness of Preventing False Discovery,” 2014. arXiv.orgAbstract
We show a tight bound on the number of adaptively chosen statistical queries that a computationally efficient algorithm can answer accurately given n samples from an unknown distribution. A statistical query asks for the expectation of a predicate over the underlying distribution, and an answer to a statistical query is accurate if it is "close" to the correct expectation over the distribution. This question was recently considered by Dwork et al., who showed that Ω~(n2) queries can be answer efficiently, and also by Hardt and Ullman, who showed that answering O~(n3) queries is computationally hard. We close the gap between the two bounds by proving a new, nearly-optimal hardness result. Specifically, we show that, under a standard hardness assumption, there is no computationally efficient algorithm that given n samples from an unknown distribution can give valid answers to O(n2) adaptively chosen statistical queries. An implication of our results is that computationally efficient algorithms for answering arbitrary, adaptively chosen statistical queries may as well be differentially private. We obtain our results via an optimal construction of a new combinatorial object that we call an interactive fingerprinting code, which may be of independent interest.
L. Waye, “Privacy Integrated Data Stream Queries,” Privacy and Security in Programming, , 2014.
V. Feldman and Xiao, D., “

Sample Complexity Bounds on Differentially Private Learning via Communication Complexity

,” Proceedings of The 27th Conference on Learning Theory (COLT 2014), , vol. 35. JMLR Workshop and Conference Proceedings, pp. 1-20, 2014. Publisher's VersionAbstract
In this work we analyze the sample complexity of classification by differentially private algorithms. Differential privacy is a strong and well-studied notion of privacy introduced by Dwork et al. (2006) that ensures that the output of an algorithm leaks little information about the data point provided by any of the participating individuals. Sample complexity of private PAC and agnostic learning was studied in a number of prior works starting with (Kasiviswanathan et al., 2008) but a number of basic questions still remain open (Beimel et al. 2010; Chaudhuri and Hsu, 2011; Beimel et al., 2013ab).  Our main contribution is an equivalence between the sample complexity of differentially-private learning of a concept class C (or SCDP(C)) and the randomized one-way communication complexity of the evaluation problem for concepts from C. Using this equivalence we prove the following bounds:
  • SCDP(C)=Ω(LDim(C)), where LDim(C) is the Littlestone's (1987) dimension characterizing the number of mistakes in the online-mistake-bound learning model. This result implies that SCDP(C) is different from the VC-dimension of C, resolving one of the main open questions from prior work.
  • For any t, there exists a class C such that LDim(C)=2 but SCDP(C)≥t.
  • For any t, there exists a class C such that the sample complexity of (pure) α-differentially private PAC learning is Ω(t/α) but the sample complexity of the relaxed (α,β)-differentially private PAC learning is O(log(1/β)/α). This resolves an open problem from (Beimel et al., 2013b). 
We also obtain simpler proofs for a number of known related results. Our equivalence builds on a characterization of sample complexity by Beimel et al., (2013a) and our bounds rely on a number of known results from communication complexity.
J. Hsu, et al., “

Privately Solving Linear Programs

,” in Automata, Languages, and Programming, , vol. 8572, Springer Berlin Heidelberg, 2014, pp. 612-624. Publisher's Version 1402.3631v2.pdf
M. M. Pai, Roth, A., and Ullman, J., “

An Anti-Folk Theorem for Large Repeated Games with Imperfect Monitoring

,” CoRR, , vol. abs/1402.2801, 2014. 1402.2801v1.pdf
D. J. Weitzner, et al., “

Consumer Privacy Bill of Rights and Big Data: Response to White House Office of Science and Technology Policy Request for Information

”. 2014.Abstract
In response to the White House Office of Science and Technology Policy Request for Information on Big Data Privacy we offer these comments based on presentations and discussions at the White House-MIT Workshop “Big Data Privacy Workshop: Advancing the State of the Art in Technology and Practice” and subsequent workshops co-sponsored with Data & Society and NYU Information Law Institute and the UC Berkeley iSchool.
PDF version
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 PDF version of comments
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
S. Hooley and Sweeney, L., “Survey of Publicly Available State Health Databases,” Data Privacy Lab, IQSS, Harvard University, . 2013. Project website PDF