Related papers: Crypto-Oriented Neural Architecture Design
Throughput limitations of existing blockchain architectures are one of the most significant hurdles for their wide-spread adoption. Attempts to address this challenge include layer-2 solutions, such as Bitcoin's Lightning or Ethereum's…
The notion that collaborative machine learning can ensure privacy by just withholding the raw data is widely acknowledged to be flawed. Over the past seven years, the literature has revealed several privacy attacks that enable adversaries…
Privacy preservation is addressed for decentralized optimization, where $N$ agents cooperatively minimize the sum of $N$ convex functions private to these individual agents. In most existing decentralized optimization approaches,…
Cloud computing enables users to process and store data remotely on high-performance computers and servers by sharing data over the Internet. However, transferring data to clouds causes unavoidable privacy concerns. Here, we present a…
Cloud-edge collaborative inference approach splits deep neural networks (DNNs) into two parts that run collaboratively on resource-constrained edge devices and cloud servers, aiming at minimizing inference latency and protecting data…
Deep learning is widely applied to modern problems through neural networks, but the growing computational and energy demands of these models have driven interest in more efficient approaches. Spiking Neural Networks (SNNs), the third…
Cryptocurrencies redefined how money can be stored and transferred among users. However, independent of the amount being sent, public blockchain-based cryptocurrencies suffer from high transaction waiting times and fees. These drawbacks…
We propose and experimentally evaluate a novel secure aggregation algorithm targeted at cross-organizational federated learning applications with a fixed set of participating learners. Our solution organizes learners in a chain and encrypts…
Over the past decade, the Bitcoin P2P network protocol has become a reference model for all modern cryptocurrencies. While nodes in this network are known, the connections among them are kept hidden, as it is commonly believed that this…
With the increasing deployment of generative machine learning models in privacy-sensitive domains such as healthcare and personalized services, ensuring secure inference has become a critical challenge. Secure multi-party computation (MPC)…
Machine learning promotes the continuous development of signal processing in various fields, including network traffic monitoring, EEG classification, face identification, and many more. However, massive user data collected for training…
Security flaws in software applications today has been attributed mostly to design flaws. With limited budget and time to release software into the market, many developers often consider security as an afterthought. Previous research shows…
In this work, we propose a novel architecture (and several variants thereof) based on quantum cryptographic primitives with provable privacy and security guarantees regarding membership inference attacks on generative models. Our…
Secure two-party computation with homomorphic encryption (HE) protects data privacy with a formal security guarantee but suffers from high communication overhead. While previous works, e.g., Cheetah, Iron, etc, have proposed efficient…
Distributed optimization and learning has recently garnered great attention due to its wide applications in sensor networks, smart grids, machine learning, and so forth. Despite rapid development, existing distributed optimization and…
We develop a layered quantum computer architecture, which is a systematic framework for tackling the individual challenges of developing a quantum computer while constructing a cohesive device design. We discuss many of the prominent…
Randomizing the address-to-set mapping and partitioning of the cache has been shown to be an effective mechanism in designing secured caches. Several designs have been proposed on a variety of rationales: (1) randomized design, (2)…
We present CryptGNN, a secure and effective inference solution for third-party graph neural network (GNN) models in the cloud, which are accessed by clients as ML as a service (MLaaS). The main novelty of CryptGNN is its secure message…
Distributed learning across a coalition of organizations allows the members of the coalition to train and share a model without sharing the data used to optimize this model. In this paper, we propose new secure architectures that guarantee…
Cryptographically Relevant Quantum Computers (CRQCs) pose a structural threat to the global digital economy. Algorithms like Shor's factoring and Grover's search threaten to dismantle the public-key infrastructure (PKI) securing sovereign…