English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper, we present VerifyML, the first secure inference framework tocheck the fairness degree of a given Machine learning (ML) model. VerifyML isgeneric and is immune to any obstruction by the malicious model holder duringthe verification process. We rely on secure two-party computation (2PC)technology to implement VerifyML, and carefully customize a series ofoptimization methods to boost its performance for both linear and nonlinearlayer execution. Specifically, (1) VerifyML allows the vast majority of theoverhead to be performed offline, thus meeting the low latency requirements foronline inference. (2) To speed up offline preparation, we first design novelhomomorphic parallel computing techniques to accelerate the authenticatedBeaver's triple (including matrix-vector and convolution triples) generationprocedure. It achieves up to $1.7\times$ computation speedup and gains at least$10.7\times$ less communication overhead compared to state-of-the-art work. (3)We also present a new cryptographic protocol to evaluate the activationfunctions of non-linear layers, which is $4\times$--$42\times$ faster and has$>48\times$ lesser communication than existing 2PC protocol against maliciousparties. In fact, VerifyML even beats the state-of-the-art semi-honest MLsecure inference system! We provide formal theoretical analysis for VerifyMLsecurity and demonstrate its performance superiority on mainstream ML modelsincluding ResNet-18 and LeNet.

VerifyML: Obliviously Checking Model Fairness Resilient to Malicious Model Holder