Related papers: Inhibitor Transformers and Gated RNNs for Torus Ef…

Transformers have become keystone models in natural language processing over the past decade. They have achieved great popularity in deep learning applications, but the increasing sizes of the parameter spaces required by transformer models…

Traditional AI methodologies necessitate centralized data collection, which becomes impractical when facing problems with network communication, data privacy, or storage capacity. Federated Learning (FL) offers a paradigm that empowers…

Much of machine learning relies on the use of large amounts of data to train models to make predictions. When this data comes from multiple sources, for example when evaluation of data against a machine learning model is offered as a…

Homomorphic Encryption (HE) prevails in securing Federated Learning (FL), but suffers from high overhead and adaptation cost. Selective HE methods, which partially encrypt model parameters by a global mask, are expected to protect privacy…

Fully Homomorphic Encryption (FHE) promises the ability to compute over encrypted data without revealing sensitive contents. However, enabling high-frequency updates and statistical analysis in outsourced databases remains elusive due to…

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…

Early neural channel coding approaches leveraged dense neural networks with one-hot encodings to design adaptive encoder-decoder pairs, improving block error rate (BLER) and automating the design process. However, these methods struggled…

Fully Homomorphic Encryption (FHE) enables privacy preserving computation but it suffers from high latency and memory consumption. The computations are secured with special keys called rotation keys which often take up the majority of…

Big data is one of the cornerstones to enabling and training deep neural networks (DNNs). Because of the lack of expertise, to gain benefits from their data, average users have to rely on and upload their private data to big data companies…

The Ring-Learning With Errors (RLWE) problem forms the backbone of highly efficient Fully Homomorphic Encryption (FHE) schemes. A significant component of the RLWE public key and ciphertext of the form $(b,a)$ is the uniformly random…

Designing hardware accelerators for deep neural networks (DNNs) has been much desired. Nonetheless, most of these existing accelerators are built for either convolutional neural networks (CNNs) or recurrent neural networks (RNNs). Recently,…

Convolutional neural networks (CNNs) have enabled significant performance leaps in medical image classification tasks. However, translating neural network models for clinical applications remains challenging due to data privacy issues.…

This paper explores the use of partially homomorphic encryption (PHE) for encrypted vector similarity search, with a focus on facial recognition and broader applications like reverse image search, recommendation engines, and large language…

The deep learning (DL) has been penetrating daily life in many domains, how to keep the DL model inference secure and sample privacy in an encrypted environment has become an urgent and increasingly important issue for various…

The hybrid hiding encryption algorithm, as its name implies, embraces concepts from both steganography and cryptography. In this exertion, an improved micro-architecture Field Programmable Gate Array (FPGA) implementation of this algorithm…

Advancements in machine learning (ML) have significantly revolutionized medical image analysis, prompting hospitals to rely on external ML services. However, the exchange of sensitive patient data, such as chest X-rays, poses inherent…

With the ubiquitous deployment of web services, ensuring data confidentiality has become a challenging imperative. Fully Homomorphic Encryption (FHE) presents a powerful solution for processing encrypted data; however, its widespread…

Privacy-preserving machine learning (PPML) solutions are gaining widespread popularity. Among these, many rely on homomorphic encryption (HE) that offers confidentiality of the model and the data, but at the cost of large latency and memory…

Machine Learning (ML) has emerged as one of data science's most transformative and influential domains. However, the widespread adoption of ML introduces privacy-related concerns owing to the increasing number of malicious attacks targeting…

Transformer neural networks (TNN) have been widely utilized on a diverse range of applications, including natural language processing (NLP), machine translation, and computer vision (CV). Their widespread adoption has been primarily driven…