Georgia Tech researchers have been awarded a $1.19 million grant from the National Science Foundation (NSF) to devise privacy protection protocols for big data cloud computing throughout all phases of data processing.
Known as PrivacyGuard, the project is a first step toward establishing a practical way of ensuring end-to-end privacy for big data computations. To achieve this, researchers at Georgia Tech’s College of Computing are working to develop protocols that split the responsibility for data privacy protection into three areas – data entry, execution, and output.
“Our goals are to develop practical solutions for enabling a ‘need to know’ privacy model, and to protect private data from any unauthorized or unintended purposes in the big data life cycle,” said School of Computer Science Professor and Lead Principal Investigator Ling Liu. “By creating a practical and systematic framework with multiple checkpoints, we increase our opportunities to catch and eliminate threats.”
Liu and her colleague on the project, Georgia Tech Professor Calton Pu, are affiliates of the Institute for Information Security and Privacy (IISP). The IISP is Georgia Tech’s hub for cybersecurity and data protection research.
The first step in creating end-to-end protection is to develop proper protocols for entering data so that sensitive information cannot be reconstructed from the final output of a big data computation. The second step is to create procedures that ensure data integrity, confidentiality, and availability are maintained during the execution phase while the information is being processed. The third protocol protects the final product of big data computations by preventing malicious users from being able to glean any sensitive information from a database.
The ability to perform efficient big data computations while preserving privacy in the cloud is critical. When these new protocols are in place, new opportunities will emerge for safe and effective data analytics. These opportunities may include healthcare applications that provide personalized medical treatments using an individual’s DNA sequence, or enabling advertisers to create targeted advertisements, without violation of data privacy.
“Big data and cloud computing are becoming more and more ubiquitous,” said Liu. “Once established, PrivacyGuard research will be integrated into Georgia Tech’s big data systems and analytics courses, contributing to the education of a new generation of data scientists that we hope will become privacy compliance advocates.”
About the Researchers:
Dr. Ling Liu, professor, School of Computer Science, College of Computing
An internationally recognized expert, Dr. Ling Liu is a professor in the College of Computing’s School of Computer Science at the Georgia Institute of Technology and an elected IEEE Fellow. She directs the research program in Distributed Data Intensive Systems program examining research issues and technical challenges in building distributed big data systems, ranging from performance, security, privacy, trust to availability. She has published more than 300 international journal and conference articles and served as a program chair for multiple IEEE and ACM conferences and is currently the editor-in-chief of IEEE Transactions on Services Computing. In addition, Dr. Liu has received numerous awards from the Institute of Electrical and Electronics Engineers, the Association for Computing Machinery, and many notable computing organizations. Professor Liu's current research is primarily sponsored by NSF, IBM, and Intel.
Dr. Calton Pu, Professor and the John P. Imlay, Jr. Chair in Software, School of Computer Science, and co-director of Center for Experimental Research in Computer Systems
Calton Pu is currently a professor and John P. Imlay, Jr. Chair in Software at the College of Computing at the Georgia Institute of Technology and an elected IEEE fellow. Dr. Pu received his Ph.D. in computer science from the University of Washington. He has worked on several projects in systems and database research and provided many contributions to systems research including program specialization and software feedback. Professor Pu's recent research has focused on automated system management in clouds, information quality, and Big Data in the Internet-of-Things. Dr. Pu has published more than 70 journal papers and book chapters and an additional 280 conference and refereed workshop papers; he has also served on more than 120 program committees. Dr. Pu's prior research included government projects for DARPA and NSF. In addition, he has conducted industry research for IBM, Intel, and HP.