An Algorithmic Framework For Differentially Private Data Analysis on Trusted Processors
By Joshua Allen, Bolin Ding, Janardhan Kulkarni, Harsha Nori, O. Ohrimenko, Sergey Yekhanin. 2018
35 citations recorded by the source corpus.
Differential privacy has emerged as the main definition for private data analysis and machine learning. The {\em 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 {\em 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 {\em 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.
Subfields: Artificial Intelligence, Information Systems
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Prateek Mittal
- Tianhao Wang
- Liwei Song
- Ninghui Li
- Somesh Jha
- Jingren Zhou
- Bolin Ding
- David Marco Sommer
In Information Systems
- Tianhao Wang
- Ninghui Li
- Somesh Jha
- Prateek Mittal
- Liwei Song
- David Marco Sommer
- Bolin Ding
- Jingren Zhou
Citations in the corpus
- Contamination Attacks and Mitigation in Multi-Party Machine Learning (2018, neutral): “Secure MPC can be enabled with cryptographic techniques [6, 11, 18, 29, 32], and systems based on trusted processors such as Intel SGX [3, 5, 33].”
- Practical and Robust Privacy Amplification with Multi-Party Differential Privacy (2019, background): “Thus [17] and [6] designed oblivious DP algorithms to overcome the threat of side information (memory access pattern may be related to the underlying data).”
- Towards Probabilistic Verification of Machine Unlearning (2020, methodology): “Possible techniques include the use of secure processors [45], trusted platform modules [46, 47], and zero-knowledge proofs [48, 49].”
- Improving utility and security of the shuffler-based differential privacy (2019, background): “Thus [18] and [6] designed oblivious DP algorithms to overcome the threat of side information (memory access pattern may be related to the underlying data).”