Gemini: Elastic SNARKs for Diverse Environments

Bootle, Jonathan; Chiesa, Alessandro; Hu, Yuncong; Orrù, Michele

doi:10.1007/978-3-031-07085-3_15

Cited by 16 publications

(1 citation statement)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We answer the question above positively in this paper by proposing a fair audit framework, which enables a publicly verifiable fairness audit of the ML model without disclosing model parameters and guarantees audit integrity of the fair audit. The main idea is to leverage the progress of zero knowledge succinct non-interactive arguments of knowledge (zk-SNAKRs) [23]- [29] recently. A zk-SNARK enables the third party to efficiently convince the verifier that the computation of fairness audit is correctly calculated.…”

Section: Introductionmentioning

confidence: 99%

Privacy-Preserving and Trustless Verifiable Fairness Audit of Machine Learning Models

Gui¹,

Tan²,

Cai³

2023

IJACSA

View full text Add to dashboard Cite

In the big data era, machine learning has developed prominently and is widely used in real-world systems. Yet, machine learning raises fairness concerns, which incurs discrimination against groups determined by sensitive attributes such as gender and race. Many researchers have focused on developing fairness audit technique of machine learning model that enable users to protect themselves from discrimination. Existing solutions, however, rely on additional external trust assumptions, either on third-party entities or external components, that significantly lower the security. In this study, we propose a trustless verifiable fairness audit framework that assesses the fairness of ML algorithms while addressing potential security issues such as data privacy, model secrecy, and trustworthiness. With succinctness and non-interactive of zero knowledge proof, our framework not only guarantees audit integrity, but also clearly enhance security, enabling fair ML models to be publicly auditable and any client to verify audit results without extra trust assumption. Our evaluation on various machine learning models and real-world datasets shows that our framework achieves practical performance.

show abstract

Section: Introductionmentioning

confidence: 99%