Rebecca Wright
Stevens Institute of Technology

Privacy-Preserving Data Mining in the Fully Distributed Model

October 17, 2005
3:30pm-4:30pm
Room 151, Computer Science Research Bldg.

Abstract: Privacy-preserving data mining seeks to balance the ability to perform useful computations on data held by many parties with the desire to protect sensitive information. In the fully distributed model, each of many users or devices has information which we think of as one record in a virtual database. In this talk, I will describe several privacy-preserving methods for computing on this virtual database. Specifically, I will present our results in two areas: (1) privacy-preserving frequency mining and (2) privacy-preserving k-anonymization. In privacy-preserving frequency mining, we present a way for a data miner to learn the frequencies of combinations of data values without learning the individual data values, and we discuss how these frequencies can enable various classification tasks. In privacy-preserving k-anonymization, we consider the previously proposed method of protecting identities in data through k-anonymization, which modifies data so that each individual is "hidden" among at least k others. Previous algorithms for k-anonymization of data have assumed centralized access to the entire data set. In our work, we show how a data miner or data publisher can learn a k-anonymized version of a fully distributed database without learning the entire data set. (Joint work with Zhiqiang Yang and Sheng Zhong.)

Biography: Rebecca Wright is an Associate Professor in the Computer Science Department at Stevens Institute of Technology in Hoboken, New Jersey. Prior to this, she was a researcher in the Secure Systems Research Department at AT&T Labs and AT&T Bell Labs from 1994 to 2002. Her research spans the area of information security, including cryptography, privacy, foundations of computer security, and fault-tolerant distributed computing. Recent work includes privacy-preserving data mining, secure multiparty approximations, and improved bounds for Byzantine agreement in the shared memory model. Her ongoing research goals are the design of protocols, systems, and services that perform their specified computational or communication functions even if some of the participants or underlying components behave maliciously, and that balance individual needs such as privacy with collective needs such as network survivability and public safety. Dr. Wright serves as an editor of the Journal of Computer Security (IOS Press) and the International Journal of Information and Computer Security (Inderscience), and is a member of the board of directors of the International Association for Cryptologic Research. She was Program Chair of Financial Cryptography 2003 and General Chair of Crypto 2002, and will be Program Chair of the 2006 ACM Conference on Computer and Communications Security (CCS). She has served on numerous program committees, including Crypto, the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, and the Usenix Security. She received a Ph.D. in Computer Science from Yale University in 1994 and a B.A. from Columbia University in 1988. She is a member of the IEEE, the ACM, and the IACR.