Timezone: »

An Algorithmic Framework For Differentially Private Data Analysis on Trusted Processors
Janardhan Kulkarni · Olga Ohrimenko · Bolin Ding · Sergey Yekhanin · Joshua Allen · Harsha Nori

Thu Dec 12 05:00 PM -- 07:00 PM (PST) @ East Exhibition Hall B + C #153

Differential privacy has emerged as the main definition for private data analysis and machine learning. The global model of differential privacy, which assumes that users trust the data collector, provides strong privacy guarantees and introduces small errors in the output. In contrast, applications of differential privacy in commercial systems by Apple, Google, and Microsoft, use the local model. Here, users do not trust the data collector, and hence randomize their data before sending it to the data collector. Unfortunately, local model is too strong for several important applications and hence is limited in its applicability. In this work, we propose a framework based on trusted processors and a new definition of differential privacy called Oblivious Differential Privacy, which combines the best of both local and global models. The algorithms we design in this framework show interesting interplay of ideas from the streaming algorithms, oblivious algorithms, and differential privacy.

Author Information

Janardhan Kulkarni (MSR, Redmond)
Olga Ohrimenko (The University of Melbourne)
Bolin Ding (Alibaba Group)
Sergey Yekhanin (Microsoft)
Joshua Allen (Microsoft)
Harsha Nori (Microsoft)

More from the Same Authors