Program profiling is widely used to measure run-time execution properties—for example, the frequency of method and statement execution. Such profiling could be applied to deployed software to gain performance insights about the behavior of many instances of the analyzed software. However, such data gathering raises privacy concerns: for example, it reveals whether (and how often) a software user accesses a particular software functionality. There is growing interest in adding privacy protections for many categories of data analyses, but such techniques have not been studied sufficiently for program event profiling.
We propose the design of privacy-preserving event frequency profiling for deployed software. Each instance of the targeted software gathers its own event frequency profile and then randomizes it. The resulting noisy data has well-defined privacy properties, characterized via the powerful machinery of differential privacy. After gathering this data from many software instances, the profiling infrastructure computes estimates of population-wide frequencies while adjusting for the effects of the randomization. The approach employs static analysis to determine constraints that must hold in all valid run-time profiles, and uses them to reduce the error of the estimates under these constraints. Our experiments study different choices for randomization and the resulting effects on the accuracy of frequency estimates. Our conclusion is that well-designed solutions can achieve both high accuracy and principled privacy-by-design for the fundamental problem of event frequency profiling.
Sat 22 FebDisplayed time zone: Pacific Time (US & Canada) change
13:00 - 14:30 | Session 2 Techniques for Specific DomainsMain Conference Chair(s): Dongyoon Lee Stony Brook University | ||
13:00 22mResearch paper | Generating Fast Sparse Matrix Vector Multiplication From a High Level Generic Functional IR Main Conference Federico Pizzuti University of Edinburgh, Michel Steuwer University of Glasgow, Christophe Dubach University of Edinburgh | ||
13:22 22mResearch paper | A Study of Event Frequency Profiling with Differential Privacy Main Conference Hailong Zhang Ohio State University, Yu Hao , Sufian Latif Ohio State University, USA, Raef Bassily Ohio State University, USA, Atanas Rountev Ohio State University | ||
13:45 22mResearch paper | Improving Database Query Performance with Automatic Fusion Main Conference Hanfeng Chen McGill University, Canada, Alexander Krolik McGill University, Canada, Bettina Kemme McGill University, Canada, Clark Verbrugge McGill University, Canada, Laurie Hendren McGill University, Canada | ||
14:07 22mResearch paper | Robust Quantization of Deep Neural Networks Main Conference Youngseok Kim Hanyang University, Korea, Junyeol Lee Hanyang University, Korea, Younghoon Kim Hanyang University, Korea, Jiwon Seo Hanyang University |