Gimme That Model!: A Trusted ML Model Trading Protocol

Laia Amoros Carafi; Syed Mahbub Hafiz; Keewoo Lee; M. Caner Tol

Gimme That Model!: A Trusted ML Model Trading Protocol

Laia Amoros Carafi, Syed Mahbub Hafiz, Keewoo Lee^*, M. Caner Tol

^*Corresponding author for this work

Department of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

Abstract

We propose a HE-based protocol for trading ML models and describe possible improvements to the protocol to make the overall transaction more efficient and secure.

Original language	English
Title of host publication	Protecting Privacy through Homomorphic Encryption
Editors	Kristin Lauter, Kim Laine, Wei Dai
Number of pages	8
Publication status	Accepted/In press - 3 Mar 2020
MoE publication type	A4 Article in a conference publication

Access to Document

https://www.microsoft.com/en-us/research/uploads/prod/2020/02/PrivateAIBootcamp2019_TechReport-team5.pdf

Fingerprint Dive into the research topics of 'Gimme That Model!: A Trusted ML Model Trading Protocol'. Together they form a unique fingerprint.

Cite this

@inproceedings{90873a0fe1014fa1a16d231246f4390b,

title = "Gimme That Model!: A Trusted ML Model Trading Protocol",

abstract = "We propose a HE-based protocol for trading ML models and describe possible improvements to the protocol to make the overall transaction more efficient and secure. ",

author = "{Amoros Carafi}, Laia and {Mahbub Hafiz}, Syed and Keewoo Lee and Tol, {M. Caner}",

year = "2020",

month = mar,

day = "3",

language = "English",

editor = "Kristin Lauter and Kim Laine and Wei Dai",

booktitle = "Protecting Privacy through Homomorphic Encryption",

}

TY - GEN

T1 - Gimme That Model!: A Trusted ML Model Trading Protocol

AU - Amoros Carafi, Laia

AU - Mahbub Hafiz, Syed

AU - Lee, Keewoo

AU - Tol, M. Caner

PY - 2020/3/3

Y1 - 2020/3/3

N2 - We propose a HE-based protocol for trading ML models and describe possible improvements to the protocol to make the overall transaction more efficient and secure.

AB - We propose a HE-based protocol for trading ML models and describe possible improvements to the protocol to make the overall transaction more efficient and secure.

M3 - Conference contribution

BT - Protecting Privacy through Homomorphic Encryption

A2 - Lauter, Kristin

A2 - Laine, Kim

A2 - Dai, Wei

ER -