Johannes Gehrke

2011 Regional Award Winner — Faculty

Johannes Gehrke

Current Position:
Tisch University Professor, Cornell University and Distinguished Engineer, Microsoft

Institution:
Cornell University and Microsoft

Discipline:
Computer Science

Recognized for: Developing the science of managing and mining large data sets

Areas of Research Interest and Expertise: Big Data, Data Science, Database systems, data mining, data privacy

Biography:

  • PhD, Computer Science, University of Wisconsin-Madison, 
  • MS, Computer Science, University of Texas at Austin

Johannes Gehrke’s research focuses on data mining and privacy.  Dr. Gehrk is the leader of Cornell’s Big Red Data Group, focusing on Big Data and Data Science.  He is the co-author of the leading textbook Database Management Systems (also known as the Cow Book). Dr. Gehrke’s research resulted in the first formal privacy guarantee for synthetic data generation, a widely used method for statistical disclosure controlled by the United States Census Bureau. The Bureau used Dr. Gehrke’s method for creating its On the Map application which analyzes labor-force indicators across wide range of geographies and worker characteristics: first time any official statistical agency worldwide released such data.

"Historically there’s little formal foundation of what it means to protect privacy. If privacy controls are too stringent, researchers have difficulty sharing information and developing more sophisticated ideas and hypotheses. But when privacy controls are too lax, the patterns that are useful in research for understanding epidemiology or economic trends might also help attackers match data to individuals."

Key Publications:

  1. Lou Y, Caruana R, Gehrke J, Hooker G. Accurate intelligible models with pairwise interactions. KDD. 2013
  2. Gupta N, Kot L, Roy S, Bender G, Gehrke J, Koch C. Entangled queries: Enabling declarative data-driven coordination. ACM Trans. Database Syst. 2012
  3. Machanavajjhala A, Kifer D, John M, Abowd JM, Gehrke J, Vilhuber L. Privacy: Theory meets Practice on the Map. ICDE. 2008

Other Honors:

2011 ACM SIGMOD Conference, Best Paper Award
2011 IEEE Computer Society Technical Achievement Award
2010 Humboldt Research Award, Alexander von Humboldt Foundation

RKE’S WEBSITE