English
Related papers

Related papers: Towards Deep Encrypted Training: Low-Latency, Memo…

200 papers

In this technical report, we explore the use of homomorphic encryption (HE) in the context of training and predicting with deep learning (DL) models to deliver strict \textit{Privacy by Design} services, and to enforce a zero-trust model of…

Image and Video Processing · Electrical Eng. & Systems 2021-10-18 Francis Dutil , Alexandre See , Lisa Di Jorio , Florent Chandelier

Homomorphic encryption (HE) is widely adopted in untrusted environments such as federated learning. A notable limitation of conventional single-key HE schemes is the stringent security assumption regarding collusion between the parameter…

Cryptography and Security · Computer Science 2023-12-29 Dongfang Zhao

The cost involved in training deep neural networks (DNNs) on von-Neumann architectures has motivated the development of novel solutions for efficient DNN training accelerators. We propose a hybrid in-memory computing (HIC) architecture for…

Hardware Architecture · Computer Science 2021-02-11 Vinay Joshi , Wangxin He , Jae-sun Seo , Bipin Rajendran

Fully Homomorphic Encryption (FHE) refers to a set of encryption schemes that allow computations to be applied directly on encrypted data without requiring a secret key. This enables novel application scenarios where a client can safely…

Machine Learning · Computer Science 2018-10-02 Roshan Dathathri , Olli Saarikivi , Hao Chen , Kim Laine , Kristin Lauter , Saeed Maleki , Madanlal Musuvathi , Todd Mytkowicz

Traditional approaches to vector similarity search over encrypted data rely on fully homomorphic encryption (FHE) to enable computation without decryption. However, the substantial computational overhead of FHE makes it impractical for…

Cryptography and Security · Computer Science 2025-02-21 Dongfang Zhao

The widespread deployment of products powered by machine learning models is raising concerns around data privacy and information security worldwide. To address this issue, Federated Learning was first proposed as a privacy-preserving…

This paper proposes Impala, a new cryptographic protocol for private inference in the client-cloud setting. Impala builds upon recent solutions that combine the complementary strengths of homomorphic encryption (HE) and secure multi-party…

Cryptography and Security · Computer Science 2022-05-16 Woo-Seok Choi , Brandon Reagen , Gu-Yeon Wei , David Brooks

We present an approach to outsourcing of training neural networks while preserving data confidentiality from malicious parties. We use fully homomorphic encryption to build a unified training approach that works on encrypted data and learns…

Cryptography and Security · Computer Science 2024-01-30 Luis Montero , Jordan Frery , Celia Kherfallah , Roman Bredehoft , Andrei Stoian

Homomorphic encryption (HE) offers data confidentiality by executing queries directly on encrypted fields in the database-as-a-service (DaaS) paradigm. While fully HE exhibits great expressiveness but prohibitive performance overhead, a…

Cryptography and Security · Computer Science 2021-11-23 Dongfang Zhao

Large scale deep learning model, such as modern language models and diffusion architectures, have revolutionized applications ranging from natural language processing to computer vision. However, their deployment in distributed or…

Leveled Homomorphic Encryption (LHE) offers a potential solution that could allow sectors with sensitive data to utilize the cloud and securely deploy their models for remote inference with Deep Neural Networks (DNN). However, this…

Machine Learning · Computer Science 2019-02-07 Moustafa AboulAtta , Matthias Ossadnik , Seyed-Ahmad Ahmadi

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…

Cryptography and Security · Computer Science 2020-01-27 M. Sadegh Riazi , Kim Laine , Blake Pelton , Wei Dai

The financial sector presents many opportunities to apply various machine learning techniques. Centralized machine learning creates a constraint which limits further applications in finance sectors. Data privacy is a fundamental challenge…

Machine Learning · Computer Science 2020-07-15 Yifei Zhang , Hao Zhu

Graph Neural Networks (GNNs) have achieved state-of-the-art performance in various graph-based learning tasks. However, enabling privacy-preserving GNNs in encrypted domains, such as under Fully Homomorphic Encryption (FHE), typically…

Cryptography and Security · Computer Science 2025-07-15 Kaixiang Zhao , Joseph Yousry Attalla , Qian Lou , Yushun Dong

Training machine learning models on data from multiple entities without direct data sharing can unlock applications otherwise hindered by business, legal, or ethical constraints. In this work, we design and implement new privacy-preserving…

Cryptography and Security · Computer Science 2024-03-27 Hamza Saleem , Amir Ziashahabi , Muhammad Naveed , Salman Avestimehr

With the popularity of cloud computing and machine learning, it has been a trend to outsource machine learning processes (including model training and model-based inference) to cloud. By the outsourcing, other than utilizing the extensive…

Cryptography and Security · Computer Science 2023-08-03 Pinglan Liu , Wensheng Zhang

Cross-silo federated learning (FL) enables multiple clients to collaboratively train a machine learning model without sharing training data, but privacy in FL remains a major challenge. Techniques using homomorphic encryption (HE) have been…

Cryptography and Security · Computer Science 2023-05-16 Jiahui Wu , Weizhe Zhang , Fucai Luo

Fully Homomorphic Encryption (FHE) enables computations directly on encrypted data, but its high computational cost remains a significant barrier. Writing efficient FHE code is a complex task requiring cryptographic expertise, and finding…

Cryptography and Security · Computer Science 2026-01-28 Bilel Sefsaf , Abderraouf Dandani , Abdessamed Seddiki , Arab Mohammed , Eduardo Chielle , Michail Maniatakos , Riyadh Baghdadi

In this paper, we address the problem of privacy-preserving federated neural network training with $N$ users. We present Hercules, an efficient and high-precision training framework that can tolerate collusion of up to $N-1$ users. Hercules…

Cryptography and Security · Computer Science 2022-07-12 Guowen Xu , Xingshuo Han , Shengmin Xu , Tianwei Zhang , Hongwei Li , Xinyi Huang , Robert H. Deng

Deep Learning as a Service (DLaaS) stands as a promising solution for cloud-based inference applications. In this setting, the cloud has a pre-learned model whereas the user has samples on which she wants to run the model. The biggest…

‹ Prev 1 8 9 10 Next ›