Sarthak Nimje, Rushab Taneja, Om Baviskar, Rachana Patil
Educational institutions face significant challenges with event attendance verification, including manual document validation, fraud risks, and delayed approval processes. This study introduces ElizaEdu, a novel decentralized AI agent system utilizing Ethereum blockchain and ElizaOS to automate and secure attendance verification workflows for academic events. The proposed system integrates autonomous AI agents to handle document validation, approval processes, and ERP integration, while utilizing blockchain technology for immutable record-keeping. The system employs four specialized agents: RequestBot for initial verification, VerifyBot for teacher validation, ApproveBot for department head confirmation, and ERPBot for automatic attendance updates. Through a 3-month pilot implementation with 120 students and 15 faculty members, ElizaEdu demonstrated an 85% reduction in verification time, complete elimination of document fraud, and 84% decrease in administrative workload. The system achieves 97.3% accuracy in document validation and 100% data integrity through blockchain verification. This study presents the architecture, implementation details, and evaluation results, demonstrating ElizaEduâs effectiveness in transforming attendance management in educational institutions.
The decentralized, open-source architecture of blockchain technology, exemplified by the Ethereum platform, has transformed online transactions by enabling secure and transparent exchanges. However, this architecture also exposes the network to various security threats that cyber attackers can exploit. Detecting suspicious behaviors in account on the Ethereum blockchain can help mitigate attacks, including phishing, Ponzi schemes, eclipse attacks, Sybil attacks, and distributed denial of service (DDoS) incidents. The proposed system introduces an ensemble stacking model combining Random Forest (RF), eXtreme Gradient Boosting (XGBoost), and a neural network (NN) to detect potential threats within the Ethereum platform. The ensemble model is fine-tuned using Bayesian optimization to enhance predictive accuracy, while explainable artificial intelligence (XAI) tools-SHAP, LIME, and ELI5-provide interpretable feature insights, improving transparency in model predictions. The dataset used comprises 9,841 Ethereum transactions across 52 initial fields (reduced to 17 relevant features), encompassing both legitimate and fraudulent records. The experimental findings demonstrate that the proposed model achieves a superior accuracy of 99.6%, outperforming that of other cutting-edge methods. These findings demonstrate that the XAI-enabled ensemble stacking model offers a highly effective, interpretable solution for blockchain security, strengthening trust and reliability within the Ethereum ecosystem.
As cryptocurrency transactions continue to grow, detecting scams within transaction records remains a critical challenge. These transactions can be represented as dynamic graphs, where Neural Network Convolution (NNConv) models are widely used for detection. However, NNConv models suffer from model decay due to evolving transaction patterns, the introduction of new users, and the emergence of adversarial techniques designed to evade detection. To address this issue, we propose an automated, periodic hyperparameter optimization method based on proximal policy optimization (PPO), a reinforcement learning algorithm designed for dynamic environments. By leveraging PPOâs stable policy updates and efficient exploration strategies, our approach continuously refines hyperparameters to sustain model performance without frequent retraining. We evaluate the proposed method on a large-scale cryptocurrency transaction dataset containing 2,973,489 nodes and 13,551,303 edges. The results demonstrate that our method achieves an F1 score of 0.9478, outperforming existing graph-based approaches. These findings validate the effectiveness of PPO-based optimization in mitigating model decay and ensuring robust cryptocurrency scam detection.
H.C. Zhang, Shike Li, Shike Li, Hang Bao ¡ 6 authors
The rapid development of blockchain technology has driven the widespread application of decentralized applications (DApps) across various fields. However, DApps cannot directly access external data and rely on oracles to interact with off-chain data. As a bridge between blockchain and external data sources, oracles pose potential risks of malicious behavior, which may inject incorrect or harmful data, leading to trust and security issues. Additionally, with the surge in data requests, the disparity in oracle trustworthiness and costs has increased, making the dynamic selection of the most suitable oracle for each request a critical challenge. To address these issues, this paper proposes a Trust-Aware and Cost-Optimized Blockchain Oracle Selection Model with Deep Reinforcement Learning (TCO-DRL). The model incorporates a comprehensive trust management mechanism to evaluate oracle reputation from multiple dimensions and employs an improved sliding time window to monitor reputation changes in real time, enhancing resistance to malicious attacks. Moreover, TCO-DRL uses deep reinforcement learning algorithms to dynamically adapt to fluctuations in oracle reputation, ensuring the selection of high-reputation oracles while optimizing node selection, thereby reducing costs without compromising data quality. We implemented and validated TCO- DRL on Ethereum. Experimental results show that, compared to existing methods, TCO-DRL reduces the allocation rate to malicious oracles by more than 39.10% and saves over 12.00% in costs. Furthermore, simulated experiments on various malicious attacks further validate the robustness and effectiveness of TCO-DRL
Mohammad Shahab Sepehri, Asal Mehradfar, Mahdi Soltanolkotabi, Salman Avestimehr
Predicting Bitcoin price remains a challenging problem due to the high volatility and complex non-linear dynamics of cryptocurrency markets. Traditional time-series models, such as ARIMA and GARCH, and recurrent neural networks, like LSTMs, have been widely applied to this task but struggle to capture the regime shifts and long-range dependencies inherent in the data. In this work, we propose CryptoMamba, a novel Mamba-based State Space Model (SSM) architecture designed to effectively capture long-range dependencies in financial time-series data. Our experiments show that CryptoMamba not only provides more accurate predictions but also offers enhanced generalizability across different market conditions, surpassing the limitations of previous models. Coupled with trading algorithms for real-world scenarios, CryptoMamba demonstrates its practical utility by translating accurate forecasts into financial outcomes. Our findings signal a huge advantage for SSMs in stock and cryptocurrency price forecasting tasks.
In this study, I propose a method for forecasting the next-day Bitcoin price range using a CART decision tree model, which integrates 124 high-dimensional technical indicators with Twitter-roBERTa sentiment analysis as the 125th feature to enhance prediction accuracy. The experiments utilize Bitcoin market data from the past six years (2019 to 2024) and approximately 58 million Twitter posts. The results demonstrate that the enhanced model, incorporating sentiment analysis, improves the average accuracy from 0.56 in the baseline modelâtrained solely on 124 technical indicatorsâto 0.62, with win rates increasing significantly by up to 45%. Sensitivity analysis further optimizes the sentiment feature weight, confirming the modelâs robustness, and provides an innovative perspective for cryptocurrency market prediction, with future applications extensible through multi-source data fusion.
ABSTRACT The burgeoning demand for blockchain technology in diverse sectors requires advanced optimization methods to improve the performance, security and privacy. However, today common blockchain mechanisms are effected by problems like suboptimal miner selection processes, susceptibility to abnormal transactions and types of attacks affecting nonânegligible parts of the ecosystem, performance bottlenecks and so forth, rendering them far from scalability and realâworld usage. This paper addresses the problem, by introducing a set of sophisticated methods that solve recent issues and enhances the robustness, scalability, confidentiality in blockchain networks. Firstly, we present âDeepMinerâ, a deep learningâbased solution that leverages historical blockchain data samples to infer optimal miner nodes. This method improves the block generation efficiency by optimizing miner node selection in realâtime, which is an essential addition to traditional random or otherwise static methods for selecting miners. Secondly, âAnoBlockâ which uses anomaly detection model to detect fraud in blockchain transactions using the statistical methods like Gaussian mixture models and isolation forests. Thirdly, âOptiChainâ uses data analytics to dynamically optimize blockchain performance by continuously evaluating live network metrics and the transaction throughout. Lastly, âPrivyChainâ which uses privacy preservation techniques such as zeroâknowledge proofs and homomorphic encryption to achieve transaction confidentiality while retaining blockchain transparency. Their solution addresses these issues with a dual approach to protect any sensitive transaction details from being leaked and make it feasible for computations over encrypted data, the result of which aligns blockchain technology with stringent privacy standards.
Bitcoin is the most valuable cryptocurrency and is renowned for its rapid and volatile price fluctuations in comparison to other currencies. This offers potential for the prediction of Bitcoin prices and has attracted the interest of researchers. Twitter (X) is one of the most widely used social media platforms. The aim of this study is to analyse the sentiment expressed in comments about bitcoin on the social media platform X using a variety of machine learning algorithms. A variety of machine learning techniques are used to classify user sentiment towards bitcoin. Moreover, the efficacy of standard bag-of-words and term frequency-inverse document frequency (TF-IDF) methods is evaluated in comparison with machine learning approaches for the purpose of expressing text as numerical vectors. Finally, a keyword ranking was performed to determine the importance of each sentiment in the development of cryptocurrencies. The bag-of-words and TF-IDF methods were used, which facilitate the representation of text-based data. The best result was obtained with the decision trees algorithm (98.74% accuracy) using the TF-IDF method. The bag-of-words method was found to produce better results in general.
Igba Emmanuel, Moral Kuve Ihimoyan, Babatunde Awotiwon, Akinkunmi Rasheed Apampa
This paper explores the integration of advanced machine learning models, including BERT, GPT, and the Prophet algorithm, with finance investment strategies to enhance predictive modeling and trend analysis in blockchain technology. The rapid evolution of blockchain has transformed financial ecosystems, offering decentralized platforms for secure and transparent transactions. However, predicting market trends and investment opportunities within this domain remains a complex challenge due to high volatility and the multifaceted nature of financial data. By leveraging the natural language processing capabilities of BERT and GPT for sentiment analysis and market behavior prediction, combined with the time-series forecasting strength of the Prophet algorithm, this study aims to provide a robust framework for analyzing blockchain-driven financial markets. Furthermore, the integration of finance investment strategies ensures practical applicability by aligning machine learning insights with real-world investment decision-making processes. The proposed approach demonstrates potential for optimizing portfolio management, enhancing risk mitigation, and improving strategic investment in blockchain ecosystems. This work bridges the gap between cutting-edge machine learning technologies and financial innovation, offering valuable insights for researchers and practitioners in both domains.
The Web3 ecosystem is increasingly evolving to multi-chain, with decentralized applications (dApps) distributing across different blockchains, which drives the need for cross-chain bridges for blockchain interoperability. However, it further opens new attack surfaces, and media outlets have reported serious attacks related to cross-chain bridges. Nevertheless, few prior research studies have studied cross-chain bridges and their related transactions, especially from a security perspective. To fill the void, this paper presents the first comprehensive analysis of cross-chain transactions. We first make efforts to create by far the largest cross-chain transaction dataset based on semantic analysis of popular cross-chain bridges, covering 13 decentralized bridges and 7 representative blockchains, with over 80 million transactions in total. Based on this comprehensive dataset, we present the landscape of cross-chain transactions from angles including token usage, user profile and the purposes of transactions, etc. We further observe that cross-chain bridges can be abused for malicious/aggressive purposes, thus we design an automated detector and deploy it in the wild to flag misbehaviors from millions of cross-chain transactions. We have identified hundreds of abnormal transactions related to exploits and arbitrages, etc. Our research underscores the prevalence of cross-chain ecosystems, unveils their characteristics, and proposes an effective detector for pinpointing security threats.
Smart contracts , being security-critical code, facilitate consensus among players and ensure secure and accurate value transfer, and formal verification is necessary to guarantee functional correctness of contracts. Game theory serves as one of the tools in formal verification by assessing whether the outcomes of contract executions meet the expected goals. While most studies employing game theory to verify smart contract functionality assume rational players, in practice, players may invoke and deploy smart contracts involving irrational behavior, casting doubt on the correctness of verification results. The aim of this study is to propose an alternative game model to verify smart contract functionality in dynamic player interactions where irrational behavior is involved. Specifically, a belief-based smart contract execution game (BSC-game) model was introduced, utilizing belief â the probability that a player believes in the irrationality of others â to capture how the irrational behavior of others affects a playerâs contract execution decisions. Reasonable economic incentives were introduced to encourage honest behavior of players. Moreover, a computationally feasible method was designed to update playersâ beliefs in large-scale dynamic smart contract executions. Theoretical analysis discloses the existence of equilibrium in the BSC-game, as well as the conditions for the number of faulty players within the systemâs fault tolerance . We conducted the simulation experiments, and verified the business-oriented smart contract written in G language by the BSC-game model. The results further indicate that although playersâ beliefs impact their decisions to execute contracts, reasonable economic incentives can motivate players to execute contracts honestly. This ensures that smart contract functionality aligns with expected goals, showing that the BSC-game model can verify and guarantee the correctness of contract functions. This new approach significantly contributes to bolstering smart contract security and credibility, positively influencing blockchain stability.
Roozbeh Sarenche, Alireza Aghabagherloo, Svetla Nikovaâ, Bart Preneel
The security of Bitcoin protocols is deeply dependent on the incentives provided to miners, which come from a combination of block rewards and transaction fees. As Bitcoin experiences more halving events, the protocol reward converges to zero, making transaction fees the primary source of miner rewards. This shift in Bitcoin's incentivization mechanism, which introduces volatility into block rewards, leads to the emergence of new security threats or intensifies existing ones. Previous security analyses of Bitcoin have either considered a fixed block reward model or a highly simplified volatile model, overlooking the complexities of Bitcoin's mempool behavior. This paper presents a reinforcement learning-based tool to develop mining strategies under a more realistic volatile model. We employ the Asynchronous Advantage Actor-Critic (A3C) algorithm, which efficiently handles dynamic environments, such as the Bitcoin mempool, to derive near-optimal mining strategies when interacting with an environment that models the complexity of the Bitcoin mempool. This tool enables the analysis of adversarial mining strategies, such as selfish mining and undercutting, both before and after difficulty adjustments, providing insights into the effects of mining attacks in both the short and long term. We revisit the Bitcoin security threshold presented in the WeRLman paper and demonstrate that the implicit predictability of valuable transaction arrivals in this model leads to an underestimation of the reported threshold. Additionally, we show that, while adversarial strategies like selfish mining under the fixed reward model incur an initial loss period of at least two weeks, the transition toward a transaction-fee era incentivizes mining pools to abandon honest mining for immediate profits. This incentive is expected to become more significant as the protocol reward approaches zero in the future.
This study presents a comparative analysis of two advanced attention-based deep learning modelsâAttention-LSTM and Attention-GRUâfor predicting Bitcoin price movements. The significance of this research lies in integrating moving average technical indicators with deep learning models to enhance sensitivity to market momentum, and in normalizing these indicators to accurately reflect market trends and reversals. Utilizing historical OHLCV data along with four key technical indicators (SMA, EMA, TEMA, and MACD), the models classify trends into uptrend, downtrend, and neutral categories. Experimental results demonstrate that the inclusion of technical indicators, particularly MACD, significantly improves prediction accuracy. Furthermore, the Attention-GRU model offers computational efficiency suitable for real-time applications, while the Attention-LSTM model excels in capturing long-term dependencies. These findings contribute valuable insights for financial forecasting, providing practical tools for cryptocurrency traders and investors.
Chon Kit Lao, Sophie Zhou, Luyao Zhang, Fan Zhang ¡ 5 authors
Blockchain systems such as Bitcoin and Ethereum have limitations in efficiency, resulting in an inability to immediately confirm all transactions, leading to extended periods of transactions residing in the mempool. We refer to these transactions as âlong latency trans- actionsâ and this paper explores the issue of resource utilization in- efficiencies issues from these transactions. Utilizing the Geth client, the study quantifies the impact of these transactions on Ethereumâs resource consumption, which encompassing three crucial metrics: computational power, memory storage, and network bandwidth. Furthermore, this study also identifies three primary factors con- tributing to long latency transactions: low gas prices, long block processing times, and future-index transactions. Through empirical analysis, this study offers insights into the transaction-handling mechanisms in Ethereum. The implications of our findings aim to contribute to the enhancement of resource efficiency within the Ethereum blockchain ecosystem.
Data trading is a crucial means of unlocking the value of Internet of Things (IoT) data. However, IoT data differs from traditional material goods due to its intangible and replicable nature. This difference leads to ambiguous data rights, confusing pricing, and challenges in matching. Additionally, centralized IoT data trading platforms pose risks such as privacy leakage. To address these issues, we propose a profit-driven distributed trading mechanism for IoT data. First, a blockchain-based trading architecture for IoT data, leveraging the transparent and tamper-proof features of blockchain technology, is proposed to establish trust between data owners and data requesters. Second, an IoT data registration method that encompasses both rights confirmation and pricing is designed. The data right confirmation method uses non-fungible token to record ownership and authenticate IoT data. For pricing, we develop an IoT data value assessment index system and introduce a pricing model based on a combination of the sparrow search algorithm and the back propagation neural network. Finally, an IoT data matching method is designed based on the Stackelberg game. This establishes a Stackelberg game model involving multiple data owners and requesters, employing a hierarchical optimization method to determine the optimal purchase strategy. The security of the mechanism is analyzed and the performance of both the pricing method and matching method is evaluated. Experiments demonstrate that both methods outperform traditional approaches in terms of error rates and profit maximization.
Muhammad Muzammil, Zhengyu Wu, Aruna Balasubramanian, Nick Nikiforakis
Ethereum Name Service (ENS) domains allow users to map human-readable names (such as gold.eth) to their cryptocurrency addresses, simplifying cryptocurrency transactions. Like traditional DNS domains, ENS domains must be periodically renewed. Failure to renew leads to expiration, making them available for others to register (a phenomenon known as dropcatching). This presents a security risk where attackers can register expired domains to leverage the residual trust associated with them and, in the context of ENS, receive transactions intended for their previous owners. In this paper, we conduct the first large-scale study on dropcatching in ENS domains. We curate and analyze a dataset comprising 3.1M ENS domains and 9.7M Ethereum transactions, finding that 241K of these domains were re-registered by new owners after expiration. Our findings indicate a preference for domains linked to high-income wallets in re-registrations. We identify 2,633 transactions that were misdirected to new owners, averaging the equivalent of thousands of US dollars. Lastly, we highlight the lack of countermeasures by digital wallet providers, and suggest straightforward approaches that they can use to minimize financial losses due to ENS dropcatching.
Bitcoinâs volatile nature has made its price prediction a sought-after mathematical model in the FinTech industry. Existing studies, however, need to look into the critical aspect of time-lagged sentiment in Bitcoin price forecasting. This omission is significant because time-lagged sentiment captures delayed market reactions that are not immediately apparent in price movements. Moreover, the correlation between time-lagged sentiment and technical indicators and the limitations of individual machine learning and deep learning models necessitates a comprehensive approach for accurate and reliable Bitcoin price predictions. This paper introduces the multimodal fusion Bitcoin (MFB), an innovative generalized multimodal fusion approach that effectively integrates BiLSTM and BiGRU layers for complex feature extraction. The model employs the BorutaShap algorithm for feature selection and utilizes attention mechanisms and spatial dropout for optimization and generalization. MFBâs training and validation use news and tweet data combined with Bitcoin technical indicators to explore the impact of time-lagged sentiment on price movements, leading to more accurate and timely market predictions. The MFB performs superior Bitcoin prediction performance, achieving 97.63% accuracy and an MAE of 0.0065. Experiments highlight MFBâs capability to outperform existing models, offering significant insights for investors in making informed decisions. MFBâs innovative methodology, particularly in next-hour Bitcoin price forecasting, marks an advancement in financial forecasting. By capturing the nuanced dynamics of market sentiment and its delayed effects, MFB is a pioneering multimodal fusion approach in the FinTech domain, revolutionizing Bitcoin price prediction.
Vid KerĹĄiÄ, SaĹĄo KarakatiÄ, Muhamed TurkanoviÄ
Zero-knowledge proofs introduce a mechanism to prove that certain computations were performed without revealing any underlying information and are used commonly in blockchain-based decentralized apps (dapps). This cryptographic technique addresses trust issues prevalent in blockchain applications, and has now been adapted for machine learning (ML) services, known as Zero-Knowledge Machine Learning (ZKML). By leveraging the distributed nature of blockchains, this approach enhances the trustworthiness of ML deployments, and opens up new possibilities for privacy-preserving and robust ML applications within dapps. This paper provides a comprehensive overview of the ZKML process and its critical components for verifying ML services on-chain. Furthermore, this paper explores how blockchain technology and smart contracts can offer verifiable, trustless proof that a specific ML model has been used correctly to perform inference, all without relying on a single trusted entity. Additionally, the paper compares and reviews existing frameworks for implementing ZKML in dapps, serving as a reference point for researchers interested in this emerging field. ⢠An analytical and synthetic review of core on-chain ZKML concepts, supported by an extensive examination of both white and grey literature, establishing a foundational understanding of the field. ⢠Through a detailed analysis, modelling, and descriptive approaches, the paper outlines the processes integral to on-chain ZKML. The study is focused on two distinct frameworks â EZKL and Orion , highlighting the differences between the two approaches, as well as the difference between the underlying ZKP systems, where the former framework is based on zk-SNARKs and the latter on zk-STARKs. ⢠A laboratory experiment, coupled with a comparative analysis and use case execution comparison, was conducted to implement basic neural networks (NNs) across the two chosen frameworks, highlighting their capabilities and limitations in supporting on-chain ZKML.
Blockchain has emerged as a solution for ensuring accurate and truthful environmental variable monitoring needed for the management of pollutants and natural resources. The immutability property of blockchain helps protect the measured data on pollution and natural resources to enable truthful reporting and effective management and control of polluting agents. However, specifics on what to measure, how to use blockchain, and highlighting which blockchain frameworks have been adopted need to be explored to fill the research gaps. Therefore, we review existing works on the use of blockchain for monitoring and managing environmental variables in this paper. Specifically, we examine existing blockchain applications on greenhouse gas emissions, solid and plastic waste, food waste, food security, water usage, and the circular economy and identify what motivates the adoption of blockchain, features sought, used blockchain frameworks and consensus algorithms, and the adopted supporting technologies to complement data sensing and reporting. We conclude the review by identifying practical works that provide implementation details for rapid adoption and remaining challenges that merit future research.
Blockchain is increasingly offered as blockchain-as-a-service (BaaS) by cloud service providers. However, configuring BaaS appropriately for optimal performance and reliability resorts to try-and-error. A key challenge is that BaaS is often perceived as a ``black-box,'' leading to uncertainties in performance and resource provisioning. Previous studies attempted to address this challenge; however, the impacts of both vertical and horizontal scaling remain elusive. To this end, we present machine learning-based models to predict network reliability and throughput based on scaling configurations. In our evaluation, the models exhibit prediction errors of ~1.9%, which is highly accurate and can be applied in the real-world.
In the Bitcoin blockchain, an entity (e.g., a gambling service) may control multiple distinct address clusters. Links (i.e., trust relationships) between these disjoint address clusters can be established when one cluster is abandoned, and a new one is formed shortly thereafter. To link the clusters across time, we have developed a deep neural network model that exploits these synchronous actions derived from unlabeled data in a self-supervised manner. This model assesses whether two clusters exhibit synchronous temporal signatures indicative of a shared entity ownership.
An Internet of Things (IoT)-enabled blockchain helps to ensure quick and efficient immutable transactions. Low-power IoT integration with the Bitcoin network has created new opportunities and difficulties for blockchain transactions. Utilising data gathered from IoT-enabled devices, this study investigates the application of ML regression models to analyse and forecast Bitcoin transaction patterns. Several ML regression algorithms, including Lasso Regression, Gradient Boosting, Extreme Boosting, Extra Tree, and Random Forest Regression, are employed to build predictive models. These models are trained using historical Bitcoin transaction data to capture intricate relationships between various transaction parameters. To ensure model robustness and generalisation, cross-validation techniques and hyperparameter tuning are also applied. The empirical results show that the Bitcoin cost prediction of blockchain transactions in terms of time series. Additionally, it highlights the possibility of fusing block- chain analytics with IoT data streams, illuminating how new technologies might work together to enhance financial institutions.
Behkish Nassirzadeh, Albert Heinle, Stefanos Leonardos, Anwar Hasan ¡ 5 authors
Blockchain integration in industries like online advertising is hindered by its connectivity limitations to off-chain data. These industries heavily rely on precise counting systems for collecting and analyzing off-chain data. This requires mechanisms, often called oracles, to feed off-chain data into smart contracts. However, current oracle solutions are ill-suited for counting systems since the oracles do not know when to expect the data, posing a significant challenge. To address this, we present CountChain, a decentralized oracle network for counting systems. In CountChain, data is received by all oracle nodes, and any node can submit a proposition request. Each proposition contains enough data to evaluate the occurrence of an event. Only randomly selected nodes participate in a game to evaluate the truthfulness of each proposition by providing proof and some stake. Finally, the propositions with the outcome of True increment the counter in a smart contract. Thus, instead of a contract calling oracles for data, in CountChain, the oracles call a smart contract when the data is available. Furthermore, we present a formal analysis and experimental evaluation of the system's parameters on over half a million data points to obtain optimal system parameters. In such conditions, our game-theoretical analysis demonstrates that a Nash equilibrium exists wherein all rational parties participate with honesty.