Vectorized Secure Evaluation of Decision Forests
Raghav Malik, Vidush Singhal, Benjamin Gottfried, Milind Kulkarni

TL;DR
This paper introduces COPSE, a system that leverages ciphertext packing in Fully Homomorphic Encryption to efficiently perform secure decision forest inference, significantly outperforming previous methods.
Contribution
COPSE is the first system to exploit ciphertext packing for decision forest inference, automatically compiling models into vectorizable primitives for secure evaluation.
Findings
COPSE outperforms existing methods by over an order of magnitude.
The system scales effectively across various decision forest models.
It automates model restructuring for efficient secure inference.
Abstract
As the demand for machine learning-based inference increases in tandem with concerns about privacy, there is a growing recognition of the need for secure machine learning, in which secret models can be used to classify private data without the model or data being leaked. Fully Homomorphic Encryption (FHE) allows arbitrary computation to be done over encrypted data, providing an attractive approach to providing such secure inference. While such computation is often orders of magnitude slower than its plaintext counterpart, the ability of FHE cryptosystems to do \emph{ciphertext packing} -- that is, encrypting an entire vector of plaintexts such that operations are evaluated elementwise on the vector -- helps ameliorate this overhead, effectively creating a SIMD architecture where computation can be vectorized for more efficient evaluation. Most recent research in this area has targeted…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
