CSE 598D / STAT 598B: Privacy in Statistical Databases
Fall 2007

Welcome to the course web page!

General Information

Course Announcement

Instructors: Aleksandra Slavkovic and Adam Smith

Syllabus, Lecture Notes, Reading

Recall that reading reports must be submitted on Angel before noon (12 p.m.) the day of the lecture.

DateSyllabusReading
Aug. 30Introduction, Overview of SDL techniques (slides) Recommended background: L. Wasserman, All of Statistics, Springer Texts in Statistics.
Sep. 6No lecture.
Sep.13 Overview of Techniques in CS literature, begin discussion of definitions (slides)
Sep. 20Statistics background: log-linear models and contingency tables (STAT 504 page).

Crypto background: definitional approach, semantic security. (board lecture, no notes)
Required reading: Additional Reading:
Sep. 27 Crypto: SFE to differential privacy (slides) Required: Additional Reading:
  • A. Dobra, S. E. Fienberg, A. Rinaldo and Y. Zhou. "Confidentiality Protection and Utility for Contingency Table Data: Algorithms and Links to Statistical Theory", Manuscript, 2007. Available from the Angel page for this class.
Oct. 4 Statistics: methods for tabular data and the role of algebraic statistics (slides (pdf))

Crypto: Achieving differential privacy (slides (pdf))
Required:
Oct. 11-Dec. 6: Student lectures, see topics below.
Dec. 13Sofya Raskhodnikova: Smooth sensitivity, sample-and-aggregate Required:

Topics and Reading for Class Presentations

Opt/req. TopicReadingDateStudent Presenting
Required k-anonymity and other cluster-based methods [slides (ppt), (pdf)] Required: Additional Reading: Oct. 11Ge Ruan
RequiredSynthetic Data Sets [slides (.pdf)]Required: Additional Reading: Oct. 18Michael Lin
Optional Utility and Risk in Tabular Protection [slides (pdf)] Required: Additional Reading: Oct. 18 Juyoun Lee
RequiredDifferential Privacy and Game Theory [slides .ppt, .pptx, pdf] Oct. 25Eric Shou
Required Privacy for Social Network Data [slides] Required: Additional Reading:
  • Michael Hay, Gerome Miklau, David Jensen, Philipp Weis, and Siddharth Srivastava. Anonymizing Social Networks University of Massachusetts, Amherst. Technical Report 2007.
  • K. Frikken and P. Golle. Private Social Network Analysis. In Workshop on Privacy in the Electronic Society (WPES) 2006.
Nov. 1Machigar Ongtang
Required Software Required:
  • μ-ARGUS and τ-ARGUS . Software and the manuals can be found at CENEX SDC.
  • A. Hundepool (2006). The ARGUS software in CENEX. Privacy in Statistical Databases, Lecture Notes in Computer Science. Springer Berlin/Heidelberg, Vol. 4302. pp.334-346.
Optional:
Nov. 1Venkatesh S. Amudhan
Optional topics
Optional Privacy in Distributed Databases Required: Additional: Nov. 15Ge Ruan
OptionalModern variants of randomized response Required: Additional Reading: Nov. 8Adam Smith
Optional Utility and Risk in Microdata [slides (pdf)] Required: Additional Reading:
  • Karr, A. F., Kohnen, C. N., Oganian, A., Reiter, J. P. and Sanil, A. P. (2006). A framework for evaluating the utility of data altered to protect confidentiality. The American Statistician, 60, pp. 224 - 232.
  • Peter-Paul de Wolf (2006). Risk, Utility and PRAM. Privacy in Statistical Databases, Lecture Notes in Computer Science. Springer Berlin/Heidelberg, Vol. 4302. pp.189-204.
  • Loredana Di Consiglio and Silvia Polettini (2006). Improving Individual Risk Estimators. Privacy in Statistical Databases, Lecture Notes in Computer Science. Springer Berlin/Heidelberg, Vol. 4302. pp.243-256.
Dec. 6Juyoun Lee
Optional Remote Access Servers Nov. 29Michael Lin
Optional Methods for Tabular Data Protection Required: Additional Reading:
Optional Methods for Microdata Protection [slides (pdf)] Required: Additional Reading: Nov. 15Eric Shou
Optional Case Studies [slides (pdf)] Optional: Nov. 29Machigar Ongtang
Optional Auditors and Query Restriction Required:
  • Krishnaram Kenthapadi, Nina Mishra, Kobbi Nissim: Simulatable Auditing. Principles of Distributed Computing (PODS) 2005, p. 118-127.
  • Nabil R. Adam and John C. Wortmann. Security-control methods for statistical databases: a comparative study. ACM Computing Surveys, Vol. 21, No. 4, December 1989. ( NB: This paper covers a broad variety of techniques, but the idea is to cover only those aspects directly relevant to query auditing. The most relevant part is Section 3 (pages 526-534), although the introduction is also very helpful.)
Optional:
  • Vitaly Shmatikov's slides: .ppt
  • Shubha Nabar, Bhaskara Marthi, Krishnaram Kenthapadi, Nina Mishra and Rajeev Motwani. Towards Robustness in Query Auditing. 32nd International Conference on Very Large Data Bases (VLDB). 2006.
Dec. 6Venkatesh S. Amudhan
Optional Differential Privacy and tabular releases Required:
Optional Lower bounds on the utility of private data analysis Required:

This material is based upon work supported by the National Science Foundation under Grant No. 0729171.
Some formatting ideas were based on Lorrie Cranor's course pages.

Adam Smith
Last modified: Wed Jul 2 22:37:20 EDT 2008