In the era of cloud computing and machine learning, data has become a highly valuable
resource. Recent history has shown that the benefits brought forth by this data driven culture …

A comparison of two encrypted numbers is an important operation needed in many machine
learning applications, for example, decision tree or neural network inference/training. An …

Abstract Recently, Li and Micciancio (ePrint 2020/1533) have proposed a passive attack on
the CKKS approximate homomorphic encryption (HE) scheme, which allows an adversary to …

With the vigorous development and gradual maturity of machine learning (ML) technologies,
the AI-assisted disease diagnosis and prediction () system has been extensively studied and …

While the practicality of secure multi-party computation (MPC) has been extensively
analyzed and improved over the past decade, we are hitting the limits of efficiency with the …

Tree-based models are among the most efficient machine learning techniques for data
mining nowadays due to their accuracy, interpretability, and simplicity. The recent …

Homomorphic encryption (HE) protects data in-use, but can be computationally expensive.
To avoid the costly bootstrapping procedure that refreshes ciphertexts, some works have …

The article is devoted to the recent scientific problem of privacy-preserving data pattern
recognition. The purposes of the work are to systematize the security models for such tasks …

Статья посвящена недавно возникшей научной проблеме обеспечения
конфиденциальности в машинном обучении. Актуальность проблемы определяется …

The classification service over a stream of data is becoming an important offering for cloud
providers, but users may encounter obstacles in providing sensitive data due to privacy …