Syed Badruddoja, R. Dantu, Yanyan He, Mark A. Thompson, Abiola Salau, Kritagya Upadhyay
{"title":"Smarter Contracts to Predict using Deep-Learning Algorithms","authors":"Syed Badruddoja, R. Dantu, Yanyan He, Mark A. Thompson, Abiola Salau, Kritagya Upadhyay","doi":"10.1109/BCCA55292.2022.9922240","DOIUrl":"https://doi.org/10.1109/BCCA55292.2022.9922240","url":null,"abstract":"Deep learning techniques can predict cognitive intelligence from large datasets involving complex computations with activation functions. However, the prediction output needs verification for trust and reliability. Moreover, these algorithms suffer from the model's provenance to keep track of model updates and developments. Blockchain smart contracts provide a trustable ledger with consensus-based decisions that assure integrity and verifiability. In addition, the immutability feature of blockchain also supports the provenance of data that can help deep learning algorithms. Nevertheless, smart contract languages cannot predict due to the absence of floating-point operations required by activation functions of neural networks. In this paper, we derive a novel method using the Taylor series expansion to compute the floating-point equivalent output for activation functions. We train the deep learning model off-chain using a standard Python programming language. Moreover, we store models and predict on-chain with blockchain smart contracts to produce a trusted forecast. Our experiment and analysis achieved an accuracy (99%) similar to popular Keras Python library models for the MNIST dataset. Furthermore, any blockchain platform can reproduce the activation function using our derived method. Last but not least, other deep learning algorithms can reuse the mathematical model to predict on-chain.","PeriodicalId":190025,"journal":{"name":"2022 Fourth International Conference on Blockchain Computing and Applications (BCCA)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121826067","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Assuring Referential Integrity in Blockchain Applications","authors":"K. Yue","doi":"10.1109/BCCA55292.2022.9921976","DOIUrl":"https://doi.org/10.1109/BCCA55292.2022.9921976","url":null,"abstract":"Blockchain technology is increasingly used for applications beyond cryptocurrencies and asset management. Taking advantage of its immutability, security, trustworthiness, auditability, reliability, and decentralized authority, these applications store rich data with nuanced internal structures, relationships, and constraints in the blockchain. Popular blockchain platforms provide very limited support for assuring logical data integrity. An important integrity constraint is the foreign key referential integrity (RI) originated from relational databases. This paper is among the first efforts on specifying and assuring RI in blockchain applications by proposing an effective JSON-based model and framework. It generalizes the concept of RI to the JSON object model, which can then be applied to document NoSQL databases as well as blockchain. The paper provides a typed graph model formulation for specifying blockchain assets and RI, and accompanying algorithms for RI assurance. A permeating application example is presented with an implementation using the proposed model in Hyperledger's Fabric, a permissioned blockchain platform.","PeriodicalId":190025,"journal":{"name":"2022 Fourth International Conference on Blockchain Computing and Applications (BCCA)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122937145","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Farzaneh Bannazadeh, Malini Manohar, Rakshit Mitra, I. A. Ridhawi, Ali Abbas, M. Guizani
{"title":"A Blockchain-enabled and AI-Supported COVID-19 Detection Method","authors":"Farzaneh Bannazadeh, Malini Manohar, Rakshit Mitra, I. A. Ridhawi, Ali Abbas, M. Guizani","doi":"10.1109/BCCA55292.2022.9922168","DOIUrl":"https://doi.org/10.1109/BCCA55292.2022.9922168","url":null,"abstract":"Given that COVID-19 symptoms might be similar to other viral infectious diseases, it becomes difficult to accurately diagnose for COVID-19 without traditional testing strategies like polymerase chain reaction (PCR) testing. As the quarantine and testing requirements have been lifted from most countries, easier and innovative testing strategies are being adopted to maintain high awareness levels in regards to the spread of the disease for both authorities and the public. This paper presents a COVID-19 detection strategy that uses Machine Learning (ML) models to accurately diagnose for the disease in patients. The Artificial Intelligence (AI)-enabled solution not only serves the purpose of detecting whether patients are diagnosed with COVID, but also to track their daily symptoms and accurately classify the type of viral disease. Different ML models are trained and tested for accuracy and prediction timings. A decentralized approach is taken for the disease prediction, and hence, blockchain is adapted within the solution to ensure the authenticity of the user data. The solution has been implemented to allow users to receive real-time disease diagnosis using a web-based interface.","PeriodicalId":190025,"journal":{"name":"2022 Fourth International Conference on Blockchain Computing and Applications (BCCA)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127411972","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Md Jobair Hossain Faruk, Mazharul Islam, Fazlul Alam, H. Shahriar, A. Rahman
{"title":"Bie Vote: A Biometric Identification Enabled Blockchain-Based Secure and Transparent Voting Framework","authors":"Md Jobair Hossain Faruk, Mazharul Islam, Fazlul Alam, H. Shahriar, A. Rahman","doi":"10.1109/BCCA55292.2022.9922588","DOIUrl":"https://doi.org/10.1109/BCCA55292.2022.9922588","url":null,"abstract":"In this research, we investigate the current trends of voting technology, online voting, and possible opportunities to adopt both blockchain technology and biometrics technology in the voting system. According to the literature review, we determine that the existing electronic voting system raises concerns in terms of transparency, security, and trust across the globe. Thus, we aim to propose a biometric-enabled and hyperledger fabric-based architectural framework for e-Voting applications to automate identity verification that shall address the existing concern. In our extension work, we are aiming to provide a high-level architectural framework and implement the system in a real-world scenario.","PeriodicalId":190025,"journal":{"name":"2022 Fourth International Conference on Blockchain Computing and Applications (BCCA)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115514074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Performance Improvement of Blockchain-based IoT Applications using Deep Learning Techniques","authors":"Rizwan Patan, R. Parizi","doi":"10.1109/BCCA55292.2022.9922342","DOIUrl":"https://doi.org/10.1109/BCCA55292.2022.9922342","url":null,"abstract":"Internet of Things (IoT) deployments have increased drastically based on third-party (fog-assisted architecture) mechanisms to store, process, and share sensor data. IoT environments are mostly vulnerable to security threats due to the lack of intrinsic security measures. Blockchain technology with an untrusty framework to establish trust communication among IoT devices becomes a major concern in lightweight IoT frameworks. To solve this trust issue, we propose a DeepIoT-Block model that combines the consensual deep learning (CDL) technique using the elliptic Diffihelman protocol to strengthen the blockchain-based data storage scheme (BDSS) and Directed Acyclic Graph (DAG) to construct the blockchain network. DeepIoT-Block has implemented using a blockchain system for IoT applications to address storage security issues. DeepIoT-Block guarantees simultaneous computational complexity and transaction efficiency. The performance of the proposed model was verified and validated for IoT-based smart road traffic data. The simulation outcomes show that our proposed model, DeepIoT-Block, is computationally efficient and secure for larger scale IoT applications.","PeriodicalId":190025,"journal":{"name":"2022 Fourth International Conference on Blockchain Computing and Applications (BCCA)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123620528","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Fraud Detection in Blockchains using Machine Learning","authors":"Baran Kiliç, A. Sen, C. Özturan","doi":"10.1109/BCCA55292.2022.9922045","DOIUrl":"https://doi.org/10.1109/BCCA55292.2022.9922045","url":null,"abstract":"Crypto crimes peaked in 2021, and recent years have shown that blockchain is not going to die but will stay with us. In addition, blockchain transaction throughputs are expected to rise, which will make the manual investigation of crimes next to impossible in the future. We need effective and automated solutions to monitor and detect fraudulent activities happening on blockchains. In this paper, we propose a system to detect the blacklisted addresses in the Ethereum blockchain. First, we collected Ethereum blockchain transaction data and blacklisted addresses. Then, we constructed the transaction graph of Ethereum and extracted features of addresses, including some global features like pagerank. Finally, we trained the models of standard machine learning algorithms and predicted the class of the addresses. Our results show that with more than 97% accuracy we can predict blacklisted addresses.","PeriodicalId":190025,"journal":{"name":"2022 Fourth International Conference on Blockchain Computing and Applications (BCCA)","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124964063","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Performance Modeling and Analysis of Hotstuff for Blockchain Consensus","authors":"Yahya Shahsavari, Kaiwen Zhang, C. Talhi","doi":"10.1109/BCCA55292.2022.9922238","DOIUrl":"https://doi.org/10.1109/BCCA55292.2022.9922238","url":null,"abstract":"Byzantine Fault-Tolerant (BFT) protocols are classical algorithms that offer a faster and more energy-efficient consensus mechanism compared to Proof-of-Work (PoW), which is typically used by cryptocurrencies such as Bitcoin. Synchronous BFT systems are hard to implement and vulnerable to attacks that aim to disrupt the synchrony of the system. Practical BFT (PBFT), which is a partially synchronous protocol, is a high-performance consensus algorithm that provides strong safety in the presence of a bounded number of faulty participants. Hotstuff is one such partially synchronous BFT State Machine Replication (SMR) protocol that aims to address the aforementioned issues. PBFT is becoming a popular choice for blockchain consensus, especially in permissioned systems (e.g. Ripple, Stellar, etc). However, it is not well understood how Hotstuff, and PBFT consensus in general, behave under varying conditions that are commonly found in blockchain networks. In this paper, we present a theoretical model for the Hotstuff consensus mechanism which accurately predicts blockchain-related metrics such as the transaction throughput and expected confirmation time using important networking parameters such as the number of replicas, link latency, and packet loss. Furthermore, we validate our model through extensive simulations carried out using OMNeT++. Our results show that Hotstuff performance degrades drastically when the number of replicas increases. We observe that with a maximum number of tolerable faulty nodes, when the number of validators is increased to 127, throughput tends to zero. As well, packet loss ratio and transaction processing time are two other factors that significantly affect the performance of Hotstuff.","PeriodicalId":190025,"journal":{"name":"2022 Fourth International Conference on Blockchain Computing and Applications (BCCA)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127783547","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Towards a middleware design for efficient blockchain oracles selection","authors":"Subhasish Goswami, S. Danish, Kaiwen Zhang","doi":"10.1109/BCCA55292.2022.9922433","DOIUrl":"https://doi.org/10.1109/BCCA55292.2022.9922433","url":null,"abstract":"Blockchain smart contracts can only operate on data available on-chain, and face a major challenge of not being able to communicate with the world outside their own network. Blockchain oracles solve this problem by bridging the gap between on-chain and off-chain data. Chainlink is one of the most widely used decentralized oracle network with competing independent data providers with distinct characteristics in terms of price, performance, security, trust, etc. As a Chainlink service purchaser with unique a service level agreement (SLA) proposal for each job, a random selection of oracles to execute a certain job can result in sub-optimal solution, that could be alleviated by another oracle data provider. Therefore, in this work, we propose a middleware design to select the best data providers available in Chainlink oracle network based on individual job's service requirements. We model the oracle selection problem as a decision optimization problem and prove it to be NP-hard. We also propose two heuristic algorithms to approximate a solution to the modelled problem. We experimentally evaluate and compare the proposed design, and conclude that the proposed middleware architecture efficiently selects the oracles in terms of performance parameters.","PeriodicalId":190025,"journal":{"name":"2022 Fourth International Conference on Blockchain Computing and Applications (BCCA)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128829472","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
David T. Shen, Cole Dumas, Callie Sardina, Lewis Tseng, M. Aloqaily
{"title":"Cholula: Fast, Fault-tolerant, and Strongly Consistent Off-chain Object Storage","authors":"David T. Shen, Cole Dumas, Callie Sardina, Lewis Tseng, M. Aloqaily","doi":"10.1109/BCCA55292.2022.9922577","DOIUrl":"https://doi.org/10.1109/BCCA55292.2022.9922577","url":null,"abstract":"Emerging security technologies such as Blockchain are prominent to secure data. Blockchain inherits the advanced principles of cryptography and decentralization. This paper explores an appropriate design for distributed object storage systems for off-chain data. Our system Cholula has the following salient features: (i) Strong consistency; (ii) Optimal fast-path latency (1 RTT when there is no conflicting write); (iii) Tolerance of Byzantine servers; (iv) Security (preventing from an imposter attack); and (v) Censorship-resistance. We present our design and evaluation in this work. We demonstrate that Cholula has a better performance than the state-of-the-art object storage system Giza (the system behind Microsoft OneDrive) and Cassandra in the context of geo-replicated off-chain data.","PeriodicalId":190025,"journal":{"name":"2022 Fourth International Conference on Blockchain Computing and Applications (BCCA)","volume":"534 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124266637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. Dirir, K. Salah, D. Svetinovic, Raja Jayaraman, Ibrar Yaqoob, S. Kanhere
{"title":"Blockchain-Based Decentralized Federated Learning","authors":"A. Dirir, K. Salah, D. Svetinovic, Raja Jayaraman, Ibrar Yaqoob, S. Kanhere","doi":"10.1109/BCCA55292.2022.9921963","DOIUrl":"https://doi.org/10.1109/BCCA55292.2022.9921963","url":null,"abstract":"Federated learning (FL) has gained great traction in recent years. It can provide a privacy-preserving mechanism to train machine learning models on hidden data. However, most of today's FL systems use a centralized server to build the global FL model. Such centralization raises trust and fairness issues stemming from the fact that the FL server may have the ability to reconstruct the original data successfully. In this paper, we propose a blockchain-based decentralized FL system. The FL process in the proposed system is composed of two stages. In the first stage, FL nodes reach a consensus on the training configurations using smart contracts. In the second stage, nodes aggregate the model updates using a novel decentralized aggregation method. The proposed system efficiently schedules aggregation tasks between decentralized nodes, handles dropouts, and detects malicious acts. We test and analyze our solution using Ethereum smart contracts and Python. The implementation and testing details of the algorithms are presented, and all codes are publicly available on GitHub.","PeriodicalId":190025,"journal":{"name":"2022 Fourth International Conference on Blockchain Computing and Applications (BCCA)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134056229","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}