8 research outputs found
Trust Evolution Game in Blockchain
No full textOne of the main concepts behind Blockchain is trustlessness, where trust is shifted to a new paradigm through Cryptoeconomics. But how can people trust a trustless system? Blockchain protocols employ incentive structures predicated on game theory mechanisms in order to encourage the players (users and miners) in the system to act honestly. Users don\u27t need to trust any single entity and there is no single point of failure that the system relies on(trustless system). In this paper, we developed an abstract game model for blockchain. The game model was for a repeated matrix game to be played by blockchain users. We studied how the game design enforces players to cooperate with each other to benefit the whole players in the network, which increase trust and make the system more trustworthy. Also, we applied two basic learning algorithms to see how the players of the game will evolve over time. We found that the players learn to cooperate in the game to get better payoffs
Artificial Intelligence Applications in Cybersecurity
No full textFor the past decades, cyber threats have been increasing significantly and are designed in a sophisticated way that is tough to detect using traditional protection tools. As a result, privacy and sensitive personal information such as credit card numbers are being continuously compromised. Therefore, it is time to find a solution that can stand against the spreading of such threats. Artificial intelligence, machine learning, and deep learning could be among the top methods of detecting cyber threats. These methods could help to improve the detection technologies and engines for computer network defense. This chapter mainly focuses on artificial intelligence in cybersecurity. The main goal of this chapter is to highlight the drawbacks of the traditional security protection tools and discuss the improvements that has been made so far by applying artificial intelligence to solve the current cybersecurity problems
Decentralized access control for IoT data using blockchain and trusted oracles
No full textThe Internet of Things (IoT) is a network of connected electromechanical devices that have limited computational, networking, and storage capabilities. IoT is now widely used in healthcare, smart cars, smart grids, smart homes, smart manufacturing, and smart cities. IoT devices sense, monitor, and collect data where it can be shared with legitimate users. IoT data can be aggregated, stored and made available by multiple IoT data hosting providers. IoT data storage, management, and access involve multiple stakeholders that many include admins, owners of IoT devices, data repository hosts and providers, normal users, etc. Decentralized control and trusted management of such IoT data become critical, in which the management and access control of data is not centralized, i.e., under the control of a single entity. To date, the available methods for for access control in IoT systems are mainly centralized. In this paper, we propose a decentralized access control system for IoT data using blockchain and trusted oracles. We use features of blockchain and smart contracts to propose a decentralized, scalable, and secure management solution for accessing IoT data. In addition, we use oracles as gateways that interface with the blockchain, IoT data hosts, and remote users to provide decentralized, trusted, and uniform source feeds for IoT data. The paper also presents architectural design, interactions, logic flow, algorithms, implementation details, along with cost, computation, and security evaluation. The full code of the developed smart contracts is made publicly available at GitHub.</p
Blockchain-Enabled Loyalty Points for Tokens as Digital Money
No full textBlockchain-enabled platforms have been hailed as disruptive to existing digital business practices and have attracted significant attention from academia and industry. While blockchain technology has been extensively applied in numerous sectors, there is limited research on its optimization of customer loyalty programs (CLPs). Few studies have explored how blockchain technology can improve CLPs, despite its endorsement by contemporary research. Blockchain technology can potentially eliminate inefficiencies in traditional loyalty programs, enhance data security and transparency, reduce costs through smart contracts, offer personalized offerings, facilitate faster rewards redemption, and foster customer engagement. This chapter aims to address this gap by proposing a conceptual framework for the integration of blockchain technology in CLPs. By adopting FATE principles, merchants and customers are incentivized to participate. CLP operators can enhance their loyalty programs, create trust in their ties with customers, and drive customer loyalty. The proposed framework is analysed using UML artefacts to illustrate efficacy in two typical scenarios-purchase and redemption. The design of a proof-of-concept is discussed and the validation of an industry-scale meta or universal CLP is suggested
Trustworthy Blockchain oracles: review, comparison, and open research challenges
No full textThe essence of blockchain smart contracts lies in the execution of business logic code in a decentralized architecture in which the execution outcomes are trusted and agreed upon by all the executing nodes. Despite the decentralized and trustless architectures of the blockchain systems, smart contracts on their own cannot access data from the external world. Instead, smart contracts interact with off-chain external data sources, called oracles, whose primary job is to collect and provide data feeds and input to smart contracts. However, there is always risk of oracles providing corrupt, malicious, or inaccurate data. In this paper, we analyze and present the notion of trust in the oracles used in blockchain ecosystems. We analyze and compare trust-enabling features of the leading blockchain oracle approaches, techniques, and platforms. Moreover, we discuss open research challenges that should be addressed to ensure secure and trustworthy blockchain oracles.<br/
Enhancing arrhythmia prediction through an adaptive deep reinforcement learning framework for ECG signal analysis
No full textHeart diseases, particularly arrhythmia, remain a leading global cause of mortality. Electrocardiography (ECG) serves as a vital tool for monitoring and mitigating arrhythmia risks. Continuous proactive monitoring entails processing ECG time series data, offering critical insights to prevent severe outcomes like heart attacks and strokes. While deep learning models are widely employed for large-scale ECG data analysis, their effectiveness requires intricate hyperparameter tuning and architecture adjustments. This study presents an innovative framework incorporating a reinforcement learning-based approach to automatically fine-tune hyperparameters for a Convolutional Neural Network (CNN) model, addressing resource consumption and complexity issues. Our proposed model optimizes hyperparameters and network configurations by maximizing a reward function, overcoming challenges associated with resource-intensive and complex deep learning models. To assess its efficacy, we compare our automated fine-tuning model against both a non-optimized baseline model and a manually fine-tuned model. The findings demonstrate that our model outperforms the alternatives, achieving a higher accuracy of 97.4 %, reduced execution time (0.33 min), and lower mean square error (0.0081). Moreover, a comprehensive evaluation of resource consumption illustrates the lightweight nature of our proposed solution, minimizing overhead and complexity. Our model consistently converges to an optimal configuration, establishing its efficiency in predicting arrhythmia. In conclusion, our reinforcement learning-based hyperparameter tuning approach presents a lightweight and efficient solution for optimizing CNN models in ECG analysis. The results underscore its superiority over non-optimized and manually fine-tuned models, positioning it as a promising method for enhancing arrhythmia prediction accuracy while minimizing resource consumption and complexity
Quadruped Robots and Canine Likeness: The Uncanny Valley Effect
No full textThis paper presents canine likeness features in robotic quadrupeds that influence their social perception. We adopted Contrastive Language-Image Pre-Training (CLIP), a neural network that has demonstrated signatures of the Uncanny Valley effect, to explore how the perception of quadrupeds evolves as their level of canine likeness intensifies. Seven models were tested, ranging from a fully robotic quadruped to a living dog with 252 images. Our findings indicate that the Uncanny Valley effect also develops in quadruped robots. This finding is a reference to selecting an appropriate level of realism for canine likeness fourlegged robots in Human-Robot Interaction (HRI)
NFT Certificates and Proof of Delivery for Fine Jewelry and Gemstones
No full textFine jewelry is a unique class of ornaments composed of precious metals and gemstones. Premium-grade metals such as gold, platinum, and sliver, and gemstones such as pearls, diamonds, rubies, and emeralds are used use to make fine jewelry. Paper-based certificates are typically issued by retailers and producers for fine jewelry and gemstones as a proof of origin, sale, ownership, history, and quality. However, paper certificates are subject to counterfeiting, loss, or theft. In this paper, we show how non-fungible tokens (NFTs) and Ethereum blockchain can be used for digital certification, proof of ownership, sale history, and quality, as well as proof of delivery for fine jewelry and gemstones.We present the proposed system design and architecture with sequence diagrams covering key interactions for jewelry production, purchase, and sale, along with algorithms related to NFT minting, auctioning, ownership management, and physical delivery. We demonstrate that our proposed NFT and blockchain-based solution can provide superior alternative in terms of verifiability, traceability, immutability, and security when compared with paper-based certification and traditional auctioning, delivery and ownership management. We make our developed smart contracts and testing scripts publicly available on GitHub
