Publications of Latanya Sweeney, Ph.D.

Data Privacy Lab (Director) Institute for Software Research International School of Computer Science Carnegie Mellon University 1301 Wean Hall Pittsburgh, PA 15213

Phone: (412) 268-4484 Fax: (412) 268-6708 Email: latanya@privacy.cs.cmu.edu WWW: http://privacy.cs.cmu.edu/people/sweeney/

Books

• The Science of Privacy. Forthcoming book publication, 215 pages.
• Towards All the Data on All the People. Forthcoming book publication, 101 pages.
• The Identifiability of Data. Forthcoming book publication, 140 pages.
• Java by-the-hand: programming foundations. Forthcoming series of four books (based on Virtual Lectures, see "Software Artifacts").
• Computer Guide (with Sylvia Barrett). Cambridge: CESS Publishing. 1983.

Chapters in Books

• Information Explosion. Confidentiality, Disclosure, and Data Access: Theory and Practical Applications for Statistical Agencies, L. Zayatz, P. Doyle, J. Theeuwes and J. Lane (eds), Urban Institute, Washington, DC, 2001.
• Datafly: a system for providing anonymity in medical data. Database Security, XI: Status and Prospects, T. Lin and S. Qian (eds), Elsevier Science, Amsterdam, 1998.

Refereed Journal Papers - Published

• Preserving Privacy by De-identifying Facial Images (with Elaine Newton and Bradley Malin). IEEE Transactions on Knowledge and Data Engineering, 17 (2) February 2005, pp. 232-243. Originally available as Carnegie Mellon University, School of Computer Science, Technical Report, CMU-CS-03-119. Pittsburgh: March 2003. Abstract, Paper: 26 pages in PS, PDF (600dpi, or 300dpi).
• Navigating Computer Science Research Through Waves of Privacy Concerns: Discussions among Computer Scientists at Carnegie Mellon University. ACM Computers and Society, 34 (1) April 2004. Originally available as Carnegie Mellon University, School of Computer Science, Technical Report CMU-CS-03-165, CMU-ISRI-03-102. Pittsburgh: July 2003. Abstract, Paper: 18 pages in PS, PDF.
• Finding Lists of People on the Web. ACM Computers and Society, 34 (1) April 2004. Originally available as Carnegie Mellon University, School of Computer Science, Technical Report CMU-CS-03-168, CMU-ISRI-03-104. Pittsburgh: June 2003. Abstract, Paper: 12 pages in PDF.
• How (not) to protect genomic data privacy in a distributed network: using trail re-identification to evaluate and design anonymity protection systems. (with Bradley Malin) Journal of Biomedical Informatics. 2004; 37(3): 179-192. Also available on MEDLINE.
• k-anonymity: a model for protecting privacy. International Journal on Uncertainty, Fuzziness and Knowledge-based Systems, 10 (5), 2002; 557-570. Since publication, received recognition award as a noteworthy work at the 2004 Workshop on Privacy Enhancing Technologies. Has been heavily cited in other academic publications.
• Achieving k-anonymity privacy protection using generalization and suppression. International Journal on Uncertainty, Fuzziness and Knowledge-based Systems, 10 (5), 2002; 571-588.
• Inferring Genotype from Clinical Phenotype through a Knowledge Based Algorithm (with Bradley Malin). Pacific Symposium on Biocomputing 2002, R.B. Altman et al. (Eds.) (World Scientific, Singapore, 2002). Also available on MEDLINE.
• Commentary: Researchers need not rely on consent or not.New England Journal of Medicine, 1998.
• Weaving technology and policy together to maintain confidentiality. Journal of Law, Medicine and Ethics. 1997, 25:98-110. Has been heavily cited in policy publications, including in the original publication of the HIPAA Privacy Rule.

Refereed Conference/Workshop Papers

• AI Technologies to Defeat Identity Theft Vulnerabilities. AAAI Spring Symposium, AI Technologies for Homeland Security, 2005.
• Mining Images in Publicly-Available Cameras for Homeland Security (with Ralph Gross). AAAI Spring Symposium, AI Technologies for Homeland Security, 2005.
• Technologies to Defeat Fraudulent Schemes Related to Email Requests (with Edoardo Airoldi and Bradley Malin). AAAI Spring Symposium, AI Technologies for Homeland Security, 2005.
• Guaranteeing anonymity when sharing medical data, the datafly system. Proceedings, Journal of the American Medical Informatics Association. Washington, DC: Hanley & Belfus, Inc., 1997. Recognition award.
• Replacing Personally-Identifying Information in Medical Records, the Scrub System. In: Cimino, JJ, ed. Proceedings, Journal of the American Medical Informatics Association. Washington, DC: Hanley & Belfus, Inc., 1996:333-337. Best paper award.
• Re-Identification of DNA through an Automated Linkage Process (with Brad Malin). Proceedings, Journal of the American Medical Informatics Association. Washington, DC: Hanley & Belfus, Inc. Nov 2001; 423-427.
• Electronic Disease Surveillance and Reporting: the eReport System (with William Malloy). Proceedings, Journal of the American Medical Informatics Association. Washington, DC: Hanley & Belfus, Inc. Nov 2001; 964.
• Determining the Identifiability of DNA Database Entries (with Brad Malin). Proceedings, Journal of the American Medical Informatics Association. Washington, DC: Hanley & Belfus, Inc. Nov 2000; 537-541.
• Foundations of Privacy Protection from a Computer Science Perspective. Proceedings, Joint Statistical Meeting, AAAS, Indianapolis, IN. 2000.
• An intelligent tutor for teaching basic computer science and Java programming to medical informatics students. Proceedings, Journal of the American Medical Informatics Association. Washington, DC: Hanley & Belfus, Inc., 1999.
• Y2K BEACON: an intelligent web-based crisis center for disseminating Year 2000 biomedical equipment compliance information (with Sylvia Barrett). Proceedings, Journal of the American Medical Informatics Association. Washington, DC: Hanley & Belfus, Inc., 1999.
• Protecting privacy when disclosing information: k-anonymity and its enforcement through generalization and suppression (with Pierangela Samarati). Proceedings of the IEEE Symposium on Research in Security and Privacy, May 1998, Oakland, CA.
• Generalizing data to provide anonymity when disclosing information (with Pierangela Samarati). ACM Principles of Database Systems. Seattle, WA, USA, 1998.
• Towards the optimal suppression of details when disclosing medical data, the use of sub-combination analysis. Proceedings, MEDINFO 98. International Medical Informatics Association. Seoul, Korea. North-Holland, 1998.
• Three computational systems for disclosing medical data in the year 1999. Proceedings, MEDINFO 98. International Medical Informatics Association. Seoul, Korea. North-Holland, 1998.
• Computational Disclosure Control for Medical Microdata. Record Linkage Workshop. Bureau of the Census. Washington, DC: 1997.

Technical Reports (excluding any subsequently published)

• Adding Semantics and Rigor to Association Rule Learning: the GenTree Approach (with Yiheng Li). Carnegie Mellon University, School of Computer Science, Technical Report, CMU-ISRI-05-101. Pittsburgh: January 2005. Abstract, Paper: 25 pages in PDF.
• A Multiparty Computation for Randomly Ordering Players and Making Random Selections (with Michael Shamos). Carnegie Mellon University, School of Computer Science, Technical Report, CMU-ISRI-04-126. Pittsburgh: July 2004. Abstract, Paper: 39 pages in PDF.
• Detecting Bio-Terrorist Attacks and Naturally Occurring Outbreaks Over a Distributed Network While Protecting Privacy and Confidentiality: the PrivaSum Protocol. (with Samuel Edo-Eket). Carnegie Mellon University, School of Computer Science, Technical Report CMU-ISRI-04-111 forthcoming.
• Privacy-Preserving Bio-terrorism Surveillance that is HIPAA-Compliant Too: the Privacert System. Carnegie Mellon University, School of Computer Science, Technical Report CMU-ISRI-04-112 forthcoming.
• Learning Semantically Robust Rules from Data (with Yiheng Li). Carnegie Mellon University, School of Computer Science, Tech Report, CMU ISRI 04-107, CMU-CALD-04-100. Pittsburgh: February 2004. Abstract, Paper: 21 pages, PDF. Under review for publication.
• Trail Re-identification: Learning Who You are From Where You Have Been (with Bradley Malin and Elaine Newton). Carnegie Mellon University, School of Computer Science, Data Privacy Laboratory Technical Report, LIDAP-WP12. Pittsburgh: February 2003. Abstract, Paper: 10 pages in PS or PDF.
• That's AI?: a history and critique of the field. Carnegie Mellon University, School of Computer Science, Technical Report, CMU-CS-03-106. Pittsburgh: January 2003. Abstract, Paper: 28 pages in PS or PDF.
• Maintaining Patient Confidentiality When Sharing Medical Data Requires a Symbiotic Relationship Between Technology and Policy. Artificial Intelligence Laboratory, Massachusetts Institute of Technology, AIWP-WP344, May 1997. (PDF)
• Power Learning: using computers as teaching machines. Massachusetts Institute of Technology, Artificial Intelligence Laboratory: Working Paper. 1998.
• Speech perception using real-time phoneme detection, the BeBe System (with Patrick Thompson). Massachusetts Institute of Technology, Laboratory for Computer Science: Tech Report MIT-LCS-TR-736. 1998.
• Towards the collection of all the data on all the people. MIT Artificial Intelligence Working Paper, 1998.
• Maintaining anonymity when sharing medical data, the datafly system. MIT Artificial Intelligence Laboratory Working Paper. Cambridge: AIWP-WP344 (1997).
• Multiple hashed binary storage of words -- tiny, fast and almost perfect. Massachusetts Institute of Technology, AI Laboratory: Working paper. 1996.

Patents and Invention Disclosures

• Rendering field-structured data sufficiently anonymous: Datafly, k-Similar.
• Apparatus and Method for Instructing Students. Intelligent tutoring system.
• Privacert Stream Editing.

Software Artifcats

Core Semantic Learning Technologies Invented

• Sprees: a finite state orthographic learning system that recognizes and generates phonologically similar spellings. This was my Masters thesis. [1995]
• Scout: an algorithm and software program that profiles a dataset to learn what fields are present and the kind of information contained within, thereby providing a semantic description of an unknown dataset. [1995]
• Database Profiling Server: an algorithm and software program that relates fields across datasets and tables, thereby identifying fields containing duplicate information across tables and fields in one table that can be reliably linked to those in another table --learning is based on the actual values that appear in the tables. [1996]
• Identifiability Server: a process and related models for determining how identifiable individuals and other entities within data may be by utilizing summary and aggregate data, e.g., Census data. A finding now cited in hundreds of articles is that "87% of the US population is uniquely identified by {date of birth, gender, 5-digit ZIP}". This work is the source of that finding when used with Census data. [1997]
• Risk Assessment Server: a system for determining how identifiable individuals within data may be by utilizing an inference engine, a taxonomy and ontology of fields, specific domain knowledge, knowledge about available datasets, and population specifics. This server is licensed commercially to perform HIPAA Certifications (see www.privacert.com); and, can be used in privacy-preserving bio-terrorism surveillance (see my AAAS Presentation and TAPAC testimony). It has also been the basis, in part, of my numerous expert witness consultations and testimonies. [1998]
• Donor Profiling and Solicitation (DPS): an algorithm and software program that learns a psychological profile of a person based on giving history, and then uses compiled information to determine an optimal personalized solicitation strategy for a given solicitation attempt. Previously licensed to CESS, Inc. and Share Systems, Inc., who used it with more than 30 leading non-profit organizations including the Democratic National Party, the National Organization for Women, the Harlem Boy's Choir, Bishop Tutu's South African Freedom Campaign, and Greenpeace. [1987]
• DPS Extractor: an algorithm and software program that learns titles, given names, surnames, suffixes, street names, and other information about a household by extracting and interpreting information from mailing labels. This was licensed to CESS, Inc. and to Share Systems, Inc. [1987]
• Biblio: an algorithm and software program that extracts publication references from raw text bibliographies, identifying constituent parts (author names, title, publication, etc.), and then uses learned information to remove duplicates and to construct a searchable database. This was licensed to CESS, Inc. and Chitin, Inc. [1988]
• Scrub Extractor: an algorithm and software program that automatically extracts names, addresses, and other identifying information from letters, notes, articles, and other free text documents. (Basis, in part, for Scrub System, which is a privacy de-identification tool described below.) [1996]
• Iterative Profiler: an algorithm and process by which increasing amounts of information is related to individuals using inferential linkages of data fragments across various kinds of data sources. This has been the basis, in part, of some of my expert witness experiments and testimonies. [1997]
• RosterFinder: an algorithm and program that uses the Google API to allow searches for web pages containing rosters (lists of names) of people. A sample use was to locate web pages containing rosters of undergraduate students in computer science; about 18,725 students were found in 39 schools. Results are available in a searchable database on-line (thanks in part to Marshall Warfield). [2003]
• CameraWatch: a suite of algorithms and programs for locating IP addresses of live webcams and webpages showing images from live webcams. A sample of the results is available in an on-line searchable database (thanks in part to Kishore Madhava). The work has been highlighted on ABC News, CNN, USA Today, and SlashDot, and has had more than a million hits to the website. [2003]
• SSNwatch: a method and process by which public information about Social Security number (SSN) allocations is used to learn past residential information and current age inferences about the person to whom the SSN was assigned. This provides a means to match a person presenting an SSN to the demographics learned about the SSN, which is useful in combating identity theft. [2004]

Data Privacy Technologies Invented

• k-Anonymity: any algorithm or process that anonymizes data by insuring each entity in the data is indistinguishable from at least a specific number of other such entities in the data. Provisional patent (US and International). Received a recognition award from the 2004 Workshop on Privacy Enhancing Technologies. Has been cited, discussed and extended in lots of academic work by others across numerous communities and applied to all kinds of data and has inspired other kinds of uses (e.g., k-anonymous messaging). [1997]
• Datafly: an algorithm and general-purpose software program that anonymizes field-structured data so that the released data adheres to a k-anonymity requirement. Specifically, there are k records that are indistinct over the fields sensitive to re-identification. Received a recognition award from the American Medical Informatics Association. A license was provided to Datanon, LLC and now subsequently to Privacert, Inc. [1997]
• k-Similar: a general-purpose clustering algorithm that groups the closest information together with the guarantee that there are at least k members to each cluster. The number of clusters is not fixed, making the algorithm the converse of the very well-known k-means cluster algorithm, which guarantees there are at least k clusters having any number of members. Like Datafly, k-Similar can be used to anonymize field-structured data so that the released data adheres to a k-anonymity requirement. But unlike Datafly, results from k-Similar maintain the maximum detail possible. A license was provided to Datanon, LLC and now subsequently to Privacert, Inc. [1998]
• k-Same (with Elaine Newton and Bradley Malin): an algorithm for de-identifying faces in video surveillance data such that no face recognition software (no matter how good the software may get) can reliably recognize the resulting images even though most facial details are preserved. This is done by averaging image components, which may be the original image pixels (k-Same-Pixel) or eigenvectors (k-Same-Eigen) so that k-anonymity is assured. [2003]
• Scrub: an algorithm and software program that anonymizes unrestricted text such that the identities of individuals and other entities in the data cannot be re-identified. (Converse of Scrub Extractor mentioned earlier.) Based on its use with clinical notes and letters, it received a recognition award from the American Medical Informatics Association in 1996. [1996]
• Policy Explorer: an algorithm and process that characterizes and quantifies data sharing practices by estimating how much information is made available about each entity that is the subject of the data and reporting related measures of risks. Provides a tool for comparing competing policies and performing “what if” analyses. [1997]
• Privacert: a rule-based system with related language ("PrivaCert Editing Language") for expressing and enforcing anonymity requirements to render a specific dataset sufficiently de-identified. Results satisfy privacy standards established by the Risk Assessment Server (mentioned above) and not necessarily k-anonymity. This technology is licensed to Privacert, Inc. for use in rendering health data sufficently de-identified in accordance to HIPAA (U.S. medical privacy regulation). [1997]
• PrivaSum (with Samuel Edo-Eket): a real-world protocol that allows parties to jointly compute an aggregate statistic over a network such that the result is known by all but the contribution by each party remains confidential. Performance is improved over the traditional secret sharing approach, which is deterministic, by providing probabilistic assurances even in the face of widespread collusion by some malicious parties. [2004]

Other Semantic Learning Technologies Invented

• Collaboration Wheel: an on-line tool for supporting group joint work on a common document in a networked environment. Java prototype built by Charles Shelton in 1997. [1997]
• Active Tutor (aka Power Learning): an on-line teaching-learning environment, where the computer plays the role of an expert teacher. Instructions and practice are seamlessly integrated and adapted to the personal needs of each student. On-line demonstration available. [1983-2002]
• Virtual lectures: By taking the expected path of an "average student" through an Active Tutor (described above), the teaching-learning material can be condensed into carefully crafted on-line lectures. Teaching-learning materials for 3 full semesters of the Java Programming language are available on-line (Java1, Java2, Java3) and have been used to teach hundreds of students in courses at Carnegie Mellon (e.g., 15-100) and Harvard University, officially, and many other schools unofficially. Numerous non-traditional students have reported using the on-line materials for self-directed learning. [1998-2002]
• GridCity: a visual programming environment in which students write Java programs to control vehicles in a GridWorld. This is an adaptation of Karel the Robot by Richard Pattis, but this adaptation exploits the fundamental programming constructs made possible by Java that were not available to Karel in Pascal. On-line demonstrations and software download available. Used by hundreds of students at Carnegie Mellon and Harvard University. [1999-2002]
• Bebe: an algorithm and software program for learning the basics sounds of a human language based on automated detection of phonemes in the analog waveform. No high-level knowledge of the language is used, so performs as well learning the Korean sound system as the American English sound system. Early implementations done jointly with Patrick Thompson. [1997]
• Iris Expert System shell: a method and software program for developing on-line expert systems for diagnostic tasks. A sampler was built for interviewing people about personal behaviors that may place them at risk to AIDS; the program received regional print and radio news coverage in New England. [1989]
• CompuFix: a software program that steps a person through the repair of a personal computer, assuming no prior knowledge of computer repairs. Uses the Iris Expert System shell (mentioned above). Was licensed to American Information Technologies, which sold copies commercially. [1990]

Theses

• Computational Disclosure Control: Theory and Practice. . Massachusetts Institute of Technology, Laboratory for Computer Science, Tech Report, PhD Thesis. 2001. Committee: Hal Abelson (Chair), Peter Szolovits, and Daniel Weitzner.
• Sprees, a Finite-State Orthographic Learning System that Recognizes and Generates Phonologically Similar Spellings. Massachusetts Institute of Technology, Artificial Intelligence Laboratory: Working paper, Masters Thesis. 1997. Finalist in MasterWorks. Thesis advisor: Peter Szolovits.
• A Coin Toss: the Dialectical Odds aren't always 50/50. Harvard University, Faculty of Arts and Sciences: Working paper, ALB Thesis. 1995. Advisors: Henry Leitner (Harvard) and Jon Doyle (MIT).

Non-academic Works by Others that Reference my Work (Selected)

Government and Policy References (Selected)

• Privacy Commissioner of Canada, Annual Report, 2000. My work is cited explicitly.
• Federal Register, March and December 2000, Health Insurance Privacy and Portability Act (HIPPA). My work is cited explicitly in supporting commentary on de-identification provisions of the Privacy Rule of HIPAA.

Popular Press Articles that Reference My Work (Selected from more than 125)

• ABC News, June 13, 2004, "University Web Site Watches Public Spies". (text)
• CNN, October 11, 2003, "Privacy researcher: Public Web cams troublesome". (text)
• USA Today, August 25, 2003, "CameraWatch, Who watches the watchmen?". (text)
• Computer World, October 14, 2002, "Privacy algorithms." (text)
• Pittsburgh Post-Gazette, August 15, 2002, "Seeing profits in privacy, recent transplant launches firm to protect individual identities." (more)
• Consumer Reports, August 2000, Section: Consumer Interest: Health and Medical Records Privacy. "Who knows your medical secrets?" pages 22-26. http://www.consumerreports.org
• Newsweek, October 16, 2000. "It Doesn't Take Much to Make You Stand Out".
• Newsday, November 21, 2000 Section: Health & Discovery, "When Medical Data Goes Public", pages C8-C10, Author Earl Lane (Washington Bureau), http://library.newsday.com/
• National Journal's Technology Daily, July 14, 2000, "Senator predicts three-pronged medical privacy plan." (text)
• Wall Street Journal, February 2001. Author Glen Simpson. Privacy of Census Data.
• 20/20 Television News Magazine [20 second clip regarding pharmacy data]
• New York Times, February 16, 2000.
• ZDNet, April 7, 1999, "Free speech and privacy forever." (text)
• Los Angeles Times, February 8, 1999, "A new push is on for Patients Privacy Law." (text)