HDCoin: A Proof-of-Useful-Work Based Blockchain for Hyperdimensional
Computing
- URL: http://arxiv.org/abs/2202.02964v1
- Date: Mon, 7 Feb 2022 06:21:29 GMT
- Title: HDCoin: A Proof-of-Useful-Work Based Blockchain for Hyperdimensional
Computing
- Authors: Dongning Ma, Sizhe Zhang, Xun Jiao
- Abstract summary: This paper introduces HDCoin, a blockchain-based framework for an emerging machine learning scheme: the brain-inspired hyperdimensional computing (HDC)
Under the HDC scenario, miners are competing to obtain the highest test accuracy on a given dataset.
The winner has its model recorded in the blockchain and are available for the public as a trustworthy HDC model.
- Score: 2.7462881838152913
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Various blockchain systems and schemes have been proposed since Bitcoin was
first introduced by Nakamoto Satoshi as a distributed ledger. However,
blockchains usually face criticisms, particularly on environmental concerns as
their ``proof-of-work'' based mining process usually consumes a considerable
amount of energy which hardly makes any useful contributions to the real world.
Therefore, the concept of ``proof-of-useful-work'' (PoUW) is proposed to
connect blockchain with practical application domain problems so the
computation power consumed in the mining process can be spent on useful
activities, such as solving optimization problems or training machine learning
models. This paper introduces HDCoin, a blockchain-based framework for an
emerging machine learning scheme: the brain-inspired hyperdimensional computing
(HDC). We formulate the model development of HDC as a problem that can be used
in blockchain mining. Specifically, we define the PoUW under the HDC scenario
and develop the entire mining process of HDCoin. During mining, miners are
competing to obtain the highest test accuracy on a given dataset. The winner
also has its model recorded in the blockchain and are available for the public
as a trustworthy HDC model. In addition, we also quantitatively examine the
performance of mining under different HDC configurations to illustrate the
adaptive mining difficulty.
Related papers
- Trusted Compute Units: A Framework for Chained Verifiable Computations [41.94295877935867]
This paper introduces the Trusted Compute Unit (TCU), a unifying framework that enables composable and interoperable computations across heterogeneous technologies.
By enabling secure off-chain interactions without incurring on-chain confirmation delays or gas fees, TCUs significantly improve system performance and scalability.
arXiv Detail & Related papers (2025-04-22T09:01:55Z) - ScaloWork: Useful Proof-of-Work with Distributed Pool Mining [0.8192907805418583]
Bitcoin blockchain uses hash-based Proof-of-Work (PoW) that prevents unwanted participants from hogging the network resources.
Most of this energy is wasted on hash calculations, which serve no additional purpose.
We present a new framework for Useful PoW, ScaloWork, that decides the block proposer for the Bitcoin blockchain based on the solution for the dominating set problem.
arXiv Detail & Related papers (2025-04-19T15:43:27Z) - Efficient Self-Supervised Video Hashing with Selective State Spaces [63.83300352372051]
Self-supervised video hashing (SSVH) is a practical task in video indexing and retrieval.<n>We introduce S5VH, a Mamba-based video hashing model with an improved self-supervised learning paradigm.
arXiv Detail & Related papers (2024-12-19T04:33:22Z) - Synergistic Development of Perovskite Memristors and Algorithms for Robust Analog Computing [53.77822620185878]
We propose a synergistic methodology to concurrently optimize perovskite memristor fabrication and develop robust analog DNNs.<n>We develop "BayesMulti", a training strategy utilizing BO-guided noise injection to improve the resistance of analog DNNs to memristor imperfections.<n>Our integrated approach enables use of analog computing in much deeper and wider networks, achieving up to 100-fold improvements.
arXiv Detail & Related papers (2024-12-03T19:20:08Z) - Active Data Curation Effectively Distills Large-Scale Multimodal Models [66.23057263509027]
Knowledge distillation (KD) is the de facto standard for compressing large-scale models into smaller ones.<n>In this work we explore an alternative, yet simple approach -- active data curation as effective distillation for contrastive multimodal pretraining.<n>Our simple online batch selection method, ACID, outperforms strong KD baselines across various model-, data- and compute-configurations.
arXiv Detail & Related papers (2024-11-27T18:50:15Z) - BlockFound: Customized blockchain foundation model for anomaly detection [47.04595143348698]
BlockFound is a customized foundation model for anomaly blockchain transaction detection.
We introduce a series of customized designs to model the unique data structure of blockchain transactions.
BlockFound is the only method that successfully detects anomalous transactions on Solana with high accuracy.
arXiv Detail & Related papers (2024-10-05T05:11:34Z) - SoK: Public Blockchain Sharding [19.82054462793622]
This study provides a systemization of knowledge of public blockchain sharding.
It includes the core components of sharding systems, challenges, limitations, and mechanisms of the latest sharding protocols.
arXiv Detail & Related papers (2024-05-30T22:38:40Z) - Gophy: Novel Proof-of-Useful-Work blockchain architecture for High Energy Physics [0.0]
The architecture is being implemented using Golang and can be run inside the CbmRoot software environment.
The blockchain features a token-based cryptocurrency that is rewarded to miners that donate computational power.
The implementation named gophy is being implemented in Golang and is expected to be open-sourced before the end of 2024.
arXiv Detail & Related papers (2024-04-13T22:34:48Z) - Enhancing Trust and Privacy in Distributed Networks: A Comprehensive Survey on Blockchain-based Federated Learning [51.13534069758711]
Decentralized approaches like blockchain offer a compelling solution by implementing a consensus mechanism among multiple entities.
Federated Learning (FL) enables participants to collaboratively train models while safeguarding data privacy.
This paper investigates the synergy between blockchain's security features and FL's privacy-preserving model training capabilities.
arXiv Detail & Related papers (2024-03-28T07:08:26Z) - Enhanced Security and Efficiency in Blockchain with Aggregated Zero-Knowledge Proof Mechanisms [15.034624246970154]
Current approaches to data verification in blockchain systems face challenges in terms of efficiency and computational overhead.
This study proposes an innovative aggregation scheme for Zero-Knowledge Proofs within the structure of Merkle Trees.
We develop a system that significantly reduces the size of the proof and the computational resources needed for its generation and verification.
arXiv Detail & Related papers (2024-02-06T09:26:46Z) - CNN-FL for Biotechnology Industry Empowered by Internet-of-BioNano
Things and Digital Twins [22.792474445441037]
Digital twins (DTs) are revolutionizing the biotechnology industry by enabling sophisticated digital representations of biological assets, microorganisms, drug development processes, and digital health applications.
However, digital twinning at micro and nano scales, particularly in modeling complex entities like bacteria, presents significant challenges in terms of requiring advanced Internet of Things infrastructure and computing approaches.
We propose a novel framework that integrates the Internet of Bio-Nano Things (IoBNT) with advanced machine learning techniques, specifically convolutional neural networks (CNN) and federated learning (FL)
arXiv Detail & Related papers (2024-01-31T23:40:44Z) - Generative AI-enabled Blockchain Networks: Fundamentals, Applications,
and Case Study [73.87110604150315]
Generative Artificial Intelligence (GAI) has emerged as a promising solution to address challenges of blockchain technology.
In this paper, we first introduce GAI techniques, outline their applications, and discuss existing solutions for integrating GAI into blockchains.
arXiv Detail & Related papers (2024-01-28T10:46:17Z) - A Blockchain Solution for Collaborative Machine Learning over IoT [2.4739484546803334]
Federated learning (FL) and blockchain technologies have emerged as promising approaches to address these challenges.<n>We present a novel IoT solution that combines the incremental learning vector quantization algorithm (XuILVQ) with blockchain technology.<n>Our proposed architecture addresses the shortcomings of existing blockchain-based FL solutions by reducing computational and communication overheads while maintaining data privacy and security.
arXiv Detail & Related papers (2023-11-23T18:06:05Z) - Learning Energy-Based Prior Model with Diffusion-Amortized MCMC [89.95629196907082]
Common practice of learning latent space EBMs with non-convergent short-run MCMC for prior and posterior sampling is hindering the model from further progress.
We introduce a simple but effective diffusion-based amortization method for long-run MCMC sampling and develop a novel learning algorithm for the latent space EBM based on it.
arXiv Detail & Related papers (2023-10-05T00:23:34Z) - Proof of Deep Learning: Approaches, Challenges, and Future Directions [0.0]
PoDL is a consensus mechanism that uses the process of training a deep learning model as proof of work to add new blocks to the blockchain.
We discuss the different types of PoDL algorithms, their advantages and disadvantages, and their potential applications.
arXiv Detail & Related papers (2023-08-31T13:49:04Z) - BPFISH: Blockchain and Privacy-preserving FL Inspired Smart Healthcare [0.3867363075280543]
This paper proposes Federated Learning (FL) based smart healthcare system where Medical Centers (MCs) train the local model using the data collected from patients and send the model weights to the miners in a blockchain-based robust framework without sharing raw data, keeping privacy preservation into deliberation.
We formulate an optimization problem by maximizing the utility and minimizing the loss function considering energy consumption and FL process delay of MCs for learning effective models on distributed healthcare data underlying a blockchain-based framework.
arXiv Detail & Related papers (2022-07-24T04:06:28Z) - An Extension to Basis-Hypervectors for Learning from Circular Data in
Hyperdimensional Computing [62.997667081978825]
Hyperdimensional Computing (HDC) is a computation framework based on properties of high-dimensional random spaces.
We present a study on basis-hypervector sets, which leads to practical contributions to HDC in general.
We introduce a method to learn from circular data, an important type of information never before addressed in machine learning with HDC.
arXiv Detail & Related papers (2022-05-16T18:04:55Z) - Quantum-resistance in blockchain networks [46.63333997460008]
This paper describes the work carried out by the Inter-American Development Bank, the IDB Lab, LACChain, Quantum Computing (CQC), and Tecnologico de Monterrey to identify and eliminate quantum threats in blockchain networks.
The advent of quantum computing threatens internet protocols and blockchain networks because they utilize non-quantum resistant cryptographic algorithms.
arXiv Detail & Related papers (2021-06-11T23:39:25Z) - Quantum Multi-Solution Bernoulli Search with Applications to Bitcoin's
Post-Quantum Security [67.06003361150228]
A proof of work (PoW) is an important cryptographic construct enabling a party to convince others that they invested some effort in solving a computational task.
In this work, we examine the hardness of finding such chain of PoWs against quantum strategies.
We prove that the chain of PoWs problem reduces to a problem we call multi-solution Bernoulli search, for which we establish its quantum query complexity.
arXiv Detail & Related papers (2020-12-30T18:03:56Z) - Faster Secure Data Mining via Distributed Homomorphic Encryption [108.77460689459247]
Homomorphic Encryption (HE) is receiving more and more attention recently for its capability to do computations over the encrypted field.
We propose a novel general distributed HE-based data mining framework towards one step of solving the scaling problem.
We verify the efficiency and effectiveness of our new framework by testing over various data mining algorithms and benchmark data-sets.
arXiv Detail & Related papers (2020-06-17T18:14:30Z) - Stochastic-based Neural Network hardware acceleration for an efficient
ligand-based virtual screening [0.6431253679501663]
Virtual Screening studies how to identify molecular compounds with the highest probability to present biological activity for a therapeutic target.
Due to the vast number of small organic compounds and the thousands of targets for which such large-scale screening can potentially be carried out, there has been an increasing interest in the research community to increase both, processing speed and energy efficiency in the screening of molecular databases.
In this work, we present a classification model describing each molecule with a single energy-based vector and propose a machine-learning system based on the use of ANNs.
arXiv Detail & Related papers (2020-06-03T20:18:15Z) - Toward Low-Cost and Stable Blockchain Networks [10.790006312359795]
We propose a blockchain mining resources allocation algorithm to reduce the mining cost in PoW-based (proof-of-work-based) blockchain networks.
arXiv Detail & Related papers (2020-02-19T06:42:33Z) - A Proof of Useful Work for Artificial Intelligence on the Blockchain [0.3599866690398789]
We describe a novel 'proof of useful work' (PoUW) protocol based on training a machine learning model on the blockchain.
Miners get a chance to create new coins after performing honest ML training work.
We outline mechanisms to reward useful work and punish malicious actors.
arXiv Detail & Related papers (2020-01-25T01:10:46Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.