HEonGPU is a high-performance library designed to optimize Fully Homomorphic Encryption (FHE) operations on Graphics Processing Unit (GPU). By leveraging the parallel processing capac- ity of GPUs, HEonGPU significantly reduces the computational overhead typically associated with FHE by executing complex operation concurrently. This allows for faster execution of homomorphic computations on encrypted data, enabling real-time applications in privacy-preserving machine learn- ing and secure...

With concerns about data privacy growing in a connected world, cryptography researchers have focused on fully homomorphic encryption (FHE) for promising machine learning as a service solutions. Recent advancements have lowered the computational cost by several orders of magnitude, but the latency of fully homomorphic neural networks remains a barrier to adoption. This work proposes using multi-exit neural networks (MENNs) to accelerate the FHE inference. MENNs are network architectures that...

Generative AI, a significant technological disruptor in recent years, has impacted domains like augmented reality, coding assistance, and text generation. However, use of these models requires users to trust the model owners with their sensitive data given as input to the model. Fully Homomorphic Encryption (FHE) offers a promising solution, and many earlier works have investigated the use this technology for machine learning as a service (MLaaS) applications. Still, these efforts do not...

Fully Homomorphic Encryption (FHE) allows computation on encrypted data. Various software libraries have implemented the approximate- arithmetic FHE scheme CKKS, which is highly useful for applications in machine learning and data analytics; each of these libraries have differing performance and features. It is useful for developers and researchers to learn details about these libraries’ performance and their differences. Some previous work has profiled FHE and CKKS implementations for...

The field of Fully Homomorphic Encryption (FHE) has seen many theoretical and computational advances in recent years, bringing the technology closer to practicality than ever before. For this reason, practitioners from neighbouring fields such as machine learning have sought to understand FHE to provide privacy to their work. Unfortunately, selecting secure and efficient parameters in FHE is a daunting task due to the many interdependencies between the parameters involved. In this work, we...

Certain applications such as FHE transciphering require randomness while operating over encrypted data. This randomness has to be obliviously generated in the encrypted domain and remain encrypted throughout the computation. Moreover, it should be guaranteed that independent-looking random coins can be obliviously generated for different computations. In this work, we consider the homomorphic evaluation of pseudorandom functions (PRFs) with a focus on practical lattice-based candidates....

Machine learning (ML) as a service has emerged as a rapidly expanding field across various industries like healthcare, finance, marketing, retail and e-commerce, Industry 4.0, etc where a huge amount of data is gen- erated. To handle this amount of data, huge computational power is required for which cloud computing used to be the first choice. However, there are several challenges in cloud computing like limitations of bandwidth, network connectivity, higher latency, etc. To address...

Fully Homomorphic Encryption (FHE) is a powerful Privacy-Enhancing Technology (PET) that enables computations on encrypted data without having access to the secret key. While FHE holds immense potential for enhancing data privacy and security, creating its practical applications is associated with many difficulties. A significant barrier is the absence of easy-to-use, standardized components that developers can utilize as foundational building blocks. Addressing this gap requires...

Approximate fully homomorphic encryption (FHE) schemes, such as the CKKS scheme (Cheon, Kim, Kim, Song, ASIACRYPT '17), are among the leading schemes in terms of efficiency and are particularly suitable for Machine Learning (ML) tasks. Although efficient, approximate FHE schemes have some inherent risks: Li and Micciancio (EUROCRYPT '21) demonstrated that while these schemes achieved the standard notion of CPA-security, they failed against a variant, $\mathsf{IND}\mbox{-}\mathsf{CPA}^D$, in...

Fully Homomorphic Encryption (FHE) is a powerful tool for performing privacy-preserving analytics over encrypted data. A promising method for FHE over real and complex numbers is approximate homomorphic encryption, instantiated with the Cheon-Kim-Kim-Song (CKKS) scheme. The CKKS scheme enables efficient evaluation for many privacy-preserving machine learning applications. While the efficiency advantages of CKKS are clear, there is currently a lot of confusion on how to securely instantiate...

In this work, we introduce FANNG-MPC, a versatile secure multi-party computation framework capable to offer active security for privacy preserving machine learning as a service (MLaaS). Derived from the now deprecated SCALE-MAMBA, FANNG is a data-oriented fork, featuring novel set of libraries and instructions for realizing private neural networks, effectively reviving the popular framework. To the best of our knowledge, FANNG is the first MPC framework to offer actively secure MLaaS in the...

Circuit privacy is an important notion in Fully Homomorphic Encryption (FHE), well-illustrated by the Machine Learning-as-a-Service scenario. A scheme is circuit private (first defined in Gentry’s PhD Thesis) if an adversary cannot learn the circuit evaluated on a ciphertext from the computation result. In this work, we first show that the BGV FHE scheme by Brakerski, Gentry and Vaikuntanathan (ITCS’12) is computationally circuit private in a semi-honest context, and then present an extended...

Fully Homomorphic Encryption (FHE) schemes are widely used cryptographic primitives for performing arbitrary computations on encrypted data. However, FHE incorporates a computationally intensive mechanism called bootstrapping, that resets the noise in the ciphertext to a lower level allowing the computation on circuits of arbitrary depth. This process can take significant time, ranging from several minutes to hours. To address the above issue, in this work, we propose an Electronic Design...

Homomorphic encryption (HE) allows computing encrypted data in the ciphertext domain without knowing the encryption key. It is possible, however, to break fully homomorphic encryption (FHE) algorithms by using side channels. This article demonstrates side-channel leakages of the Microsoft SEAL HE library. The proposed attack can steal encryption keys during the key generation phase by abusing the leakage of ternary value assignments that occurs during the number theoretic transform (NTT)...

The increased popularity of Machine Learning as a Service (MLaaS) makes the privacy of user data and network weights a critical concern. Using Torus FHE (TFHE) offers a solution for privacy-preserving computation in a cloud environment by allowing computation directly over encrypted data. However, software TFHE implementations of cyphertext-cyphertext multiplication needed when both input data and weights are encrypted are either lacking or are too slow. This paper proposes a new way to...

Ring-Learning-with-Errors (RLWE) has emerged as the foundation of many important techniques for improving security and privacy, including homomorphic encryption and post-quantum cryptography. While promising, these techniques have received limited use due to their extreme overheads of running on general-purpose machines. In this paper, we present a novel vector Instruction Set Architecture (ISA) and microarchitecture for accelerating the ring-based computations of RLWE. The ISA, named B512,...

Privacy enhancing technologies (PETs) have been proposed as a way to protect the privacy of data while still allowing for data analysis. In this work, we focus on Fully Homomorphic Encryption (FHE), a powerful tool that allows for arbitrary computations to be performed on encrypted data. FHE has received lots of attention in the past few years and has reached realistic execution times and correctness. More precisely, we explain in this paper how we apply FHE to tree-based models and get...

Fully homomorphic encryption (FHE) is an encryption method that allows to perform computation on encrypted data, without decryption. FHE preserves the privacy of the users of online services that handle sensitive data, such as health data, biometrics, credit scores and other personal information. A common way to provide a valuable service on such data is through machine learning and, at this time, Neural Networks are the dominant machine learning model for unstructured data. In this work...

Secure inference of deep convolutional neural networks (CNNs) under RNS-CKKS involves polynomial approximation of unsupported non-linear activation functions. However, existing approaches have three main limitations: 1) Inflexibility: The polynomial approximation and associated homomorphic evaluation architecture are customized manually for each CNN architecture and do not generalize to other networks. 2) Suboptimal Approximation: Each activation function is approximated instead of the...

Bootstrapping is a term used very often in the context of Fully Homomorphic Encryption (FHE). Anyone who is familiar with FHE knows that bootstrapping is the most sophisticated and compute-intensive component of an FHE scheme. However, very few non-FHE-experts understand what the bootstrapping operation really is and that there are various bootstrapping methods, each with its own tradeoffs. The goal of this paper is to provide a high-level introduction to common bootstrapping methods and...

In the current context of the increasing need for data privacy and quantum computing no longer being just a novel concept, Fully Homomorphic Encryption presents us with numerous quantum-secure schemes which have the concept of enabling data processing over encrypted data while not decrypting it behind. While not entirely usable at the present time, recent research has underlined its practical uses applied to databases, cloud computing, machine learning, e-voting, and IoT computing. In this...

With the development of sequencing technologies, viral strain classification -- which is critical for many applications, including disease monitoring and control -- has become widely deployed. Typically, a lab (client) holds a viral sequence, and requests classification services from a centralized repository of labeled viral sequences (server). However, such ``classification as a service'' raises privacy concerns. In this paper we propose a privacy-preserving viral strain classification...

A (single server) private information retrieval (PIR) allows a client to read data from a public database held on a remote server, without revealing to the server which locations she is reading. In a doubly efficient PIR (DEPIR), the database is first preprocessed, but the server can subsequently answer any client's query in time that is sub-linear in the database size. Prior work gave a plausible candidate for a public-key variant of DEPIR, where a trusted party is needed to securely...

Inverse sqrt and sqrt function have numerous applications in linear algebra and machine learning such as vector normalisation, eigenvalue computation, dimensionality reduction, clustering, etc. This paper presents a method to approximate and securely perform the inverse sqrt function using CKKS homomorphic encryption scheme. Since the CKKS homomorphic scheme allows only computation of polynomial functions, we propose a method to approximate the inverse sqrt function polynomially. In the end,...

Quantum information has the property that measurement is an inherently destructive process. This feature is most apparent in the principle of complementarity, which states that mutually incompatible observables cannot be measured at the same time. Recent work by Broadbent and Islam (TCC 2020) builds on this aspect of quantum mechanics to realize a cryptographic notion called certified deletion. While this remarkable notion enables a classical verifier to be convinced that a (private-key)...

Recently, the standard ResNet-20 network was successfully implemented on residue number system variant Cheon-Kim-Kim-Song (RNS-CKKS) scheme using bootstrapping, but the implementation lacks practicality due to high latency and low security level. To improve the performance, we first minimize total bootstrapping runtime using multiplexed parallel convolution that collects sparse output data for multiple channels compactly. We also propose the \emph{imaginary-removing bootstrapping} to prevent...

The emergence of cloud-computing has raised important privacy questions about the data that users share with remote servers. While data in transit is protected using standard techniques like Transport Layer Security (TLS), most cloud providers have unrestricted plaintext access to user data at the endpoint. Fully Homomorphic Encryption (FHE) offers one solution to this problem by allowing for arbitrarily complex computations on encrypted data without ever needing to decrypt it....

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 efficient instantiation of this operation in the context of fully homomorphic encryption (FHE) can be challenging, especially when a relatively high precision is sought. The conventional FHE way of evaluating the comparison operation, which is based on the sign function evaluation using FHEW/TFHE bootstrapping...

Machine learning as a service (MLaaS) has risen to become a prominent technology due to the large development time, amount of data, hardware costs, and level of expertise required to develop a machine learning model. However, privacy concerns prevent the adoption of MLaaS for applications with sensitive data. A promising privacy preserving solution is to use fully homomorphic encryption (FHE) to perform the ML computations. Recent advancements have lowered computational costs by several...

Fully homomorphic encryption (FHE) is one of the prospective tools for privacy-preserving machine learning (PPML), and several PPML models have been proposed based on various FHE schemes and approaches. Although the FHE schemes are known as suitable tools to implement PPML models, previous PPML models on FHE such as CryptoNet, SEALion, and CryptoDL are limited to only simple and non-standard types of machine learning models. These non-standard machine learning models are not proven efficient...

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 come at a cost of potential data leakage. Such breaches have a devastating impact on individuals and industry, and lead the community to seek privacy preserving solutions. A promising approach is to utilize Fully Homomorphic Encryption (FHE) to enable machine learning over encrypted data, thus providing resiliency...

Federated learning (FL) is an emerging distributed machine learning paradigm which addresses critical data privacy issues in machine learning by enabling clients, using an aggregation server (aggregator), to jointly train a global model without revealing their training data. Thereby, it improves not only privacy but is also efficient as it uses the computation power and data of potentially millions of clients for training in parallel. However, FL is vulnerable to so-called inference attacks...

The Cheon-Kim-Kim-Song (CKKS) scheme (Asiacrypt'17) is one of the most promising homomorphic encryption (HE) schemes as it enables privacy-preserving computing over real (or complex) numbers. It is known that bootstrapping is the most challenging part of the CKKS scheme. Further, homomorphic evaluation of modular reduction is the core of the CKKS bootstrapping, but as modular reduction is not represented by the addition and multiplication of complex numbers, approximate polynomials for...

This work concerns secure protocols in the massively parallel computation (MPC) model, which is one of the most widely-accepted models for capturing the challenges of writing protocols for the types of parallel computing clusters which have become commonplace today (MapReduce, Hadoop, Spark, etc.). Recently, the work of Chan et al. (ITCS '20) initiated this study, giving a way to compile any MPC protocol into a secure one in the common random string model, achieving the standard secure...

With the ongoing developments in artificial intelligence (AI), big data, and cloud services, fully homomorphic encryption (FHE) is being considered as a solution for preserving the privacy and security in machine learning systems. Currently, the existing FHE schemes are constructed using lattice-based cryptography. In state-of-the-art algorithms, a huge amount of computational resources are required for homomorphic multiplications and the corresponding bootstrapping that is necessary to...

Since Cheon et al. introduced an approximate homomorphic encryption scheme for complex numbers called Cheon-Kim-Kim-Song (CKKS) scheme, it has been widely used and applied in real-life situations, such as privacy-preserving machine learning. The polynomial approximation of a modulus reduction is the most difficult part of the bootstrapping for the CKKS scheme. In this paper, we cast the problem of finding an approximate polynomial for a modulus reduction into an L2-norm minimization...

The $k$-nearest neighbors ($k$NN) classifier predicts a class of a query, $q$, by taking the majority class of its $k$ neighbors in an existing (already classified) database, $S$. In secure $k$NN, $q$ and $S$ are owned by two different parties and $q$ is classified without sharing data. In this work we present a classifier based on $k$NN, that is more efficient to implement with homomorphic encryption (HE). The efficiency of our classifier comes from a relaxation we make to consider $\kappa$...

With the rapid increase in cloud computing, concerns surrounding data privacy, security, and confidentiality also have been increased significantly. Not only cloud providers are susceptible to internal and external hacks, but also in some scenarios, data owners cannot outsource the computation due to privacy laws such as GDPR, HIPAA, or CCPA. Fully Homomorphic Encryption (FHE) is a groundbreaking invention in cryptography that, unlike traditional cryptosystems, enables computation on...

We present a fully homomorphic encryption scheme continuing the line of works of Ducas and Micciancio (2015, [DM15]), Chillotti et al. (2016, [CGGI16a]; 2017, [CGGI17]; 2018, [CGGI18a]), and Gao (2018,[Gao18]). Ducas and Micciancio (2015) show that homomorphic computation of one bit operation on LWE ciphers can be done in less than a second, which is then reduced by Chillotti et al. (2016, 2017, 2018) to 13ms. According to Chillotti et al. (2018, [CGGI18b]), the cipher expansion for TFHE is...

The rise of machine learning as a service multiplies scenarios where one faces a privacy dilemma: either sensitive user data must be revealed to the entity that evaluates the cognitive model (e.g., in the Cloud), or the model itself must be revealed to the user so that the evaluation can take place locally. Fully Homomorphic Encryption (FHE) offers an elegant way to reconcile these conflicting interests in the Cloud-based scenario and also preserve non-interactivity. However, due to the...

Neural Networks (NN) are today increasingly used in Machine Learning where they have become deeper and deeper to accurately model or classify high-level abstractions of data. Their development however also gives rise to important data privacy risks. This observation motives Microsoft researchers to propose a framework, called Cryptonets. The core idea is to combine simplifications of the NN with Fully Homomorphic Encryptions (FHE) techniques to get both confidentiality of the manipulated...

Fully Homomorphic Encryption (FHE) schemes are conceptually very powerful tools for outsourcing computations on confidential data. However, experience shows that FHE-based solutions are not sufficiently efficient for practical applications yet. Hence, there is a huge interest in improving the performance of applying FHE to concrete use cases. What has been mainly overlooked so far is that not only the FHE schemes themselves contribute to the slowdown, but also the choice of data encoding....