Related papers: Public-Decay Homomorphic State Space Models for Pr…
State space models (SSMs) have recently shown promising results on small-scale sequence and language modelling tasks, rivalling and outperforming many attention-based approaches. In this paper, we propose a multi-head state space (MH-SSM)…
As the application of deep learning continues to grow, so does the amount of data used to make predictions. While traditionally, big-data deep learning was constrained by computing performance and off-chip memory bandwidth, a new constraint…
Machine learning on encrypted data can address the concerns related to privacy and legality of sharing sensitive data with untrustworthy service providers. Fully Homomorphic Encryption (FHE) is a promising technique to enable machine…
This paper proposes a new homomorphic functional encryption using modular multiplications over a hidden ring. Unlike traditional homomorphic encryption where users can only passively perform ciphertext addition or multiplication, the…
Modern cloud inference creates a two sided privacy problem where users reveal sensitive inputs to providers, while providers must execute proprietary model weights inside potentially leaky execution environments. Fully homomorphic…
Deep learning has become a cornerstone of modern machine learning. It relies heavily on vast datasets and significant computational resources for high performance. This data often contains sensitive information, making privacy a major…
Homomorphic Encryption (HE) enables secure computation on encrypted data without decryption, allowing a great opportunity for privacy-preserving computation. In particular, domains such as healthcare, finance, and government, where data…
Convolutional neural network (CNN) inference using fully homomorphic encryption (FHE) is a promising private inference (PI) solution due to the capability of FHE that enables offloading the whole computation process to the server while…
Brakerski showed that linearly decryptable fully homomorphic encryption (FHE) schemes cannot be secure in the chosen plaintext attack (CPA) model. In this paper, we show that linearly decryptable FHE schemes cannot be secure even in the…
Outsourced computation for neural networks allows users access to state of the art models without needing to invest in specialized hardware and know-how. The problem is that the users lose control over potentially privacy sensitive data.…
Order-preserving encryption (OPE) is a fundamental cryptographic tool for enabling efficient range queries on encrypted data in outsourced databases. Despite its importance, existing OPE schemes face critical limitations that hinder their…
Federated learning (FL) has come forward as a critical approach for privacy-preserving machine learning in healthcare, allowing collaborative model training across decentralized medical datasets without exchanging clients' data. However,…
Fully Homomorphic Encryption (FHE) relies heavily on the Number Theoretic Transform (NTT), making NTT a major performance bottleneck due to its intensive polynomial computations. Hybrid Homomorphic Encryption (HHE), which integrates…
We consider an architecture of confidential cloud-based control synthesis based on Homomorphic Encryption (HE). Our study is motivated by the recent surge of data-driven control such as deep reinforcement learning, whose heavy computational…
We present the first theoretical convergence analysis of machine learning training under fully homomorphic encryption (FHE), combined with a differentially private (DP) training algorithm tailored to encrypted computation. Our approach…
Fully Homomorphic Encryption (FHE) is known to be extremely computationally-intensive, application-specific accelerators emerged as a powerful solution to narrow the performance gap. Nonetheless, due to the increasing complexities in FHE…
In recent years, Semantic Communication (SemCom), which aims to achieve efficient and reliable transmission of meaning between agents, has garnered significant attention from both academia and industry. To ensure the security of…
The processing of sensitive user data using deep learning models is an area that has gained recent traction. Existing work has leveraged homomorphic encryption (HE) schemes to enable computation on encrypted data. An early work was…
State space models (SSMs) have demonstrated state-of-the-art sequence modeling performance in some modalities, but underperform attention in language modeling. Moreover, despite scaling nearly linearly in sequence length instead of…
Privacy-preserving solutions enable companies to offload confidential data to third-party services while fulfilling their government regulations. To accomplish this, they leverage various cryptographic techniques such as Homomorphic…