PPCA: Privacy-preserving Principal Component Analysis Using Secure Multiparty Computation(MPC)

Abstract

Privacy-preserving data mining has become an important topic. People have built several multi-party-computation (MPC)-based frameworks to provide theoretically guaranteed privacy, the poor performance of real-world algorithms have always been a challenge. Using Principal Component Analysis (PCA) as an example, we show that by considering the unique performance characters of the MPC platform, we can design highly effective algorithm-level optimizations, such as replacing expensive operators and batching up. We achieve about 200× performance boost over existing privacy-preserving PCA algorithms with the same level of privacy guarantee. Also, using real-world datasets, we show that by combining multi-party data, we can achieve better training results. CCS CONCEPTS• Security and privacy → Usability in security and privacy.

Privacy Preserving Ultra-Short-term Wind Power Prediction Based on Secure Multi Party Computation

“…Similiar to other main-stream privacy-preserving applications [45,46,47], we define our security model as honestmajority and semi-honest model [48] for practical performance. The above model assumes that during the ciphertext computation, no more than a half computation servers are corrupted together ( < 2 ) and the corrupted servers will follow the agreed protocol while try to learn as much information as possible about the others.…”

“…To make MPC general (i.e., to support arbitrary functions), researchers and engineers have proposed so-called general-purpose MPC platforms, which offers a series of basic secure operations like secure addition, subtraction, multiplication, comparison which can be composed together to support complex functions like square-root and division and more advanced functions like machine-learning functions (e.g., secure principal component analysis [47]). All the secure basic operations are cryptographic protocols among the computation servers and preserve the privacy of the secret input during the computation.…”

Privacy-Preserving Machine Learning: Methods, Challenges and Directions

“…Note that PrivPy does not make a theoretical breakthrough in cryptographic protocols but instead building a practical system that enables elegant ML programming on mixed MPC frameworks and makes the right tradeoffs between efficiency and security. As a follow-up work of PrivPy, Fan et al [171] focus on the privacy-preserving principal component analysis (PCA) via demonstrating an end-to-end optimization of a data mining algorithm to run on the mixed-protocol MPC framework. To further improve the efficiency, CRYPTGPU [172] is proposed to accelerate the mixed-protocol MPC computation via GPU.…”

Performance analysis of perturbation-based privacy preserving techniques: an experimental perspective

“…Data randomly moves in this manner from high-dimensional to low-dimensional space [23]. In the geometric perturbation approach, perturbation is performed using a mixture of several techniques, including rotation transformation, translation transformation, and adding random value [24]- [26].…”