Syed Badruddoja

Syed Badruddoja

Assistant Professor -Computer Science

Posts by Collection

certifications

diversity

Diversity1

title: “Diversity Statement” collection: diversity

portfolio

publications

Integrating DOTS With Blockchain Can Secure Massive IoT Sensors

Published in 2020 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), 2020

This paper presents a novel approach to securing IoT devices by leveraging DDoS Open Threat Signaling (DOTS) architecture on a Blockchain framework. Like many areas of the information technology domain, IoT sensors are also prone to attacks but on a larger scale. There are millions of devices being connected to a central domain to provide different types of services. Since these low-powered IoT devices have constrained technical requirements with less computational capabilities, they lack the capacity to judge their behavior as benign or malignant. IoT relies heavily on the higher level of intelligent nodes to decide on their status. An IoT Controller/Edge server handles the registration and the limited management of devices. Since traditional security is unable to protect the IoT environment sufficiently, we present a Blockchain-based DDoS detection approach to secure and mitigate such attacks in the IoT environment. Our test setup includes dataset from four sensors over two months. These values were tested using a threshold calculation against the variation of temperature, humidity, pressure, and wind direction on that day to find out whether an IoT sensor is under a DDoS attack. Our results show how DOTS can help in detection of attack when mapped on IoT edge computing.

Download here

Making Smart Contracts Smarter

Published in 2021 IEEE International Conference on Blockchain and Cryptocurrency (ICBC), 2021

Blockchain technology develops static smart contracts for decentralized business transactions, lacks dynamic decision-making capabilities that limit the possibilities of ever-increasing demands of modern business applications. Artificial intelligence, a computational prediction platform provides intelligent predictions, actions, and recognition that lacks the ability to hold on to the integrity of the prediction result and requires the help of external authorities to secure the system. Blockchain-based AI prediction can cover the gaps of individual technologies and can mutually benefit from one another to develop a decentralized machine learning architecture that promises to yield better security, automation, and dynamism of the application. This paper proposes a Naive Bayes prediction algorithm to perform prediction with inside blockchain smart contracts that promises to open up more opportunities in the field of Blockchain-AI decentralized applications.

Download here

Scalable Smart Contracts for Linear Regression Algorithm

Published in EAI BlockTEA 2022 - 2nd EAI International Conference on Blockchain Technology and Emerging Applications, 2022

Linear regression algorithms capture information from previous experiences and build a cognitive model to forecast the future. The information and the cognitive model representing the history of predicting future outputs must be reliable so that expected results are trusted. Furthermore, the algorithms must be explainable and traceable, making the learning process meaningful and trackable. Blockchain smart contracts boost information integrity, providing trust and the provenance of distributed ledger transactions that support such requirements. Smart contracts are traditionally developed to perform simple transactions with integer operations. However, developing learning algorithms such as linear regression with smart contracts mandates complex computation involving floating-point operations, which are not supported by smart contracts. Moreover, smart contract transactions are expensive and time-consuming. In this work, we propose a novel implementation of smart contracts for linear regression algorithms with fraction-based computation that can train and predict on the Ethereum blockchain. Our smart contract-based training and prediction technique with Solidity programming language produced a similar mean square error to the scikit-learn-based prediction model. Moreover, our design strategy saves training costs for linear regression algorithms through off-chain computations with an optimistic roll-up solution. The off-chain training and on-chain prediction strategy demonstrated in our work will help academic and industry researchers to develop cost-effective distributed AI applications in the future.

Trusted AI with Blockchain to Empower Metaverse

Published in 2022 Fourth International Conference on Blockchain Computing and Applications (BCCA), 2022

The digital experience emerging in the virtual world is a reality with the advent of the metaverse. Augmented reality(AR), virtual reality(VR), extended reality(XR), and artificial intelligence(AI) algorithms would pave the way for an immersive experience for the users in the virtual space. However, the explosion of these technologies broaches new challenges to threaten the success of metaverse due to security risks. The blockchain technology augmented with AI promises to deliver a trusted metaverse for everyone. Nevertheless, smart contracts fail to produce a cognitive prediction, dissuading users from confiding in the metaverse. We arm smart contracts with intelligence to predict using AI algorithms. Moreover, we deploy the smart contracts on the Ethereum blockchain platform and produce a prediction accuracy of 95% compared to Python scikit-learn-based predictions. Our results show that the prediction delay can obstruct the growth of metaverse applications to accept blockchain technologies. Furthermore, the limitation of blockchain technology can make integration unreasonable. Therefore, we discuss possible scalability solutions that can be part of our future work to help more metaverse applications adopt blockchain solutions.

Download here

Scalable Smart Contracts for Linear Regression Algorithm

Published in EAI BlockTEA 2022 - 2nd EAI International Conference on Blockchain Technology and Emerging Applications, 2022

Linear regression algorithms capture information from previous experiences and build a cognitive model to forecast the future. The information and the cognitive model representing the history of predicting future outputs must be reliable so that expected results are trusted. Furthermore, the algorithms must be explainable and traceable, making the learning process meaningful and trackable. Blockchain smart contracts boost information integrity, providing trust and the provenance of distributed ledger transactions that support such requirements. Smart contracts are traditionally developed to perform simple transactions with integer operations. However, developing learning algorithms such as linear regression with smart contracts mandates complex computation involving floating-point operations, which are not supported by smart contracts. Moreover, smart contract transactions are expensive and time-consuming. In this work, we propose a novel implementation of smart contracts for linear regression algorithms with fraction-based computation that can train and predict on the Ethereum blockchain. Our smart contract-based training and prediction technique with Solidity programming language produced a similar mean square error to the scikit-learn-based prediction model. Moreover, our design strategy saves training costs for linear regression algorithms through off-chain computations with an optimistic roll-up solution. The off-chain training and on-chain prediction strategy demonstrated in our work will help academic and industry researchers to develop cost-effective distributed AI applications in the future.

Scalable Smart Contracts for Linear Regression Algorithm

Published in EAI BlockTEA 2022 - 2nd EAI International Conference on Blockchain Technology and Emerging Applications, 2022

Linear regression algorithms capture information from previous experiences and build a cognitive model to forecast the future. The information and the cognitive model representing the history of predicting future outputs must be reliable so that expected results are trusted. Furthermore, the algorithms must be explainable and traceable, making the learning process meaningful and trackable. Blockchain smart contracts boost information integrity, providing trust and the provenance of distributed ledger transactions that support such requirements. Smart contracts are traditionally developed to perform simple transactions with integer operations. However, developing learning algorithms such as linear regression with smart contracts mandates complex computation involving floating-point operations, which are not supported by smart contracts. Moreover, smart contract transactions are expensive and time-consuming. In this work, we propose a novel implementation of smart contracts for linear regression algorithms with fraction-based computation that can train and predict on the Ethereum blockchain. Our smart contract-based training and prediction technique with Solidity programming language produced a similar mean square error to the scikit-learn-based prediction model. Moreover, our design strategy saves training costs for linear regression algorithms through off-chain computations with an optimistic roll-up solution. The off-chain training and on-chain prediction strategy demonstrated in our work will help academic and industry researchers to develop cost-effective distributed AI applications in the future.

Scalable Smart Contracts for Linear Regression Algorithm

Published in EAI BlockTEA 2022 - 2nd EAI International Conference on Blockchain Technology and Emerging Applications, 2022

Linear regression algorithms capture information from previous experiences and build a cognitive model to forecast the future. The information and the cognitive model representing the history of predicting future outputs must be reliable so that expected results are trusted. Furthermore, the algorithms must be explainable and traceable, making the learning process meaningful and trackable. Blockchain smart contracts boost information integrity, providing trust and the provenance of distributed ledger transactions that support such requirements. Smart contracts are traditionally developed to perform simple transactions with integer operations. However, developing learning algorithms such as linear regression with smart contracts mandates complex computation involving floating-point operations, which are not supported by smart contracts. Moreover, smart contract transactions are expensive and time-consuming. In this work, we propose a novel implementation of smart contracts for linear regression algorithms with fraction-based computation that can train and predict on the Ethereum blockchain. Our smart contract-based training and prediction technique with Solidity programming language produced a similar mean square error to the scikit-learn-based prediction model. Moreover, our design strategy saves training costs for linear regression algorithms through off-chain computations with an optimistic roll-up solution. The off-chain training and on-chain prediction strategy demonstrated in our work will help academic and industry researchers to develop cost-effective distributed AI applications in the future.

Scalable Smart Contracts for Linear Regression Algorithm

Published in EAI BlockTEA 2022 - 2nd EAI International Conference on Blockchain Technology and Emerging Applications, 2022

Linear regression algorithms capture information from previous experiences and build a cognitive model to forecast the future. The information and the cognitive model representing the history of predicting future outputs must be reliable so that expected results are trusted. Furthermore, the algorithms must be explainable and traceable, making the learning process meaningful and trackable. Blockchain smart contracts boost information integrity, providing trust and the provenance of distributed ledger transactions that support such requirements. Smart contracts are traditionally developed to perform simple transactions with integer operations. However, developing learning algorithms such as linear regression with smart contracts mandates complex computation involving floating-point operations, which are not supported by smart contracts. Moreover, smart contract transactions are expensive and time-consuming. In this work, we propose a novel implementation of smart contracts for linear regression algorithms with fraction-based computation that can train and predict on the Ethereum blockchain. Our smart contract-based training and prediction technique with Solidity programming language produced a similar mean square error to the scikit-learn-based prediction model. Moreover, our design strategy saves training costs for linear regression algorithms through off-chain computations with an optimistic roll-up solution. The off-chain training and on-chain prediction strategy demonstrated in our work will help academic and industry researchers to develop cost-effective distributed AI applications in the future.

Making Smart Contracts Predict and Scale

Published in 2022 Fourth International Conference on Blockchain Computing and Applications (BCCA), 2022

The machine learning algorithms can predict the events based on the trained models and datasets. However, a reliable prediction requires the model to be trusted and tamper-resistant. Blockchain technology provides trusted output with consensus-based transactions and an immutable distributed ledger. The machine learning algorithms can be trained on blockchain smart contracts to produce trusted models for reliable prediction. But most smart contracts in the blockchain do not support floating point data type, limiting computations for classification, which can affect the prediction accuracy. In this work, we propose a novel method to produce floating point equivalent probability estimation to classify labels on-chain with a Naive Bayes algorithm. We derive a mathematical model with Taylor series expansion to compute the ratio of the posterior probability of classes to classify labels using integers. Moreover, we implemented our solution in Ethereum blockchain smart contract with the Solidity programming language, where we achieved a prediction accuracy comparable to the scikit-learn library in Python. Our derived method is platform-agnostic and can be supported in any blockchain network. Furthermore, machine learning and deep-learning algorithms can borrow the derived method.

Download here

research

talks

teaching

Teaching Assistant

Undergraduate and Graduate Course", Department of Computer Science & Engineering, University of North Texas, 1900

Courses

Teaching Fellow

Undergraduate course, University of North Texas, Department of Computer Science & Engineering, 1900

Responsibilities

  • Prepare course curriculum, assignments, schedules, exams, and quizzes