Federated learning (FL) enables multiple participants to collaboratively train machine learning models while ensuring their data remains private and secure. Blockchain technology further enhances FL by providing stronger security, a transparent audit trail, and protection against data tampering and model manipulation. Most blockchain-secured FL systems rely on conventional consensus mechanisms: Proof-of-Work (PoW) is computationally expensive, while Proof-of-Stake (PoS) improves energy efficiency but risks centralization as it inherently favors participants with larger stakes. Recently, learning-based consensus has emerged as an alternative by replacing cryptographic tasks with model training to save energy. However, this approach introduces potential privacy vulnerabilities, as the training process may inadvertently expose sensitive information through gradient sharing and model updates. To address these challenges, we propose a novel Zero-Knowledge Proof of Training (ZKPoT) consensus mechanism. This method leverages the zero-knowledge succinct non-interactive argument of knowledge proof (zk-SNARK) protocol to validate participants' contributions based on their model performance, effectively eliminating the inefficiencies of traditional consensus methods and mitigating the privacy risks posed by learning-based consensus. We analyze our system's security, demonstrating its capacity to prevent the disclosure of sensitive information about local models or training data to untrusted parties during the entire FL process. Extensive experiments demonstrate that our system is robust against privacy and Byzantine attacks while maintaining accuracy and utility without trade-offs, scalable across various blockchain settings, and efficient in both computation and communication.
This study empirically analyzes the transaction activity of Bitcoin addresses linked to Russian intelligence services, which have liquidated over 7 Bitcoin (BTC), i.e., equivalent to approximately US$300,000 based on the exchange rate at the time. Our investigation begins with an observed anomaly in transaction outputs featuring the Bitcoin Script operation code, tied to input addresses identified by cyber threat intelligence sources and court documents as belonging to Russian intelligence agencies. We explore how an unauthorized entity appears to have gained control of the associated private keys, with messages embedded in the outputs confirming the seizure. Tracing the funds' origins, we connect them to cryptocurrency mixers and establish a link to the Russian ransomware group Conti, implicating intelligence service involvement. This analysis represents one of the first empirical studies of large-scale Bitcoin misuse by nation-state cyber actors.
Atomic swaps have been widely considered to be an ideal solution for cross-chain cryptocurrency transactions due to their trustless and decentralized nature. However, their adoption in practice has been strictly limited compared to centralized exchange order books because of long transaction times (anywhere from 20 to 60 minutes) prohibiting market makers from accurately pricing atomic swap spreads. For the decentralized finance ecosystem to expand and benefit all users, this would require accommodating market makers and high-frequency traders to reduce spreads and dramatically boost liquidity. This white paper will introduce a protocol for atomic swaps that eliminates the need for an intermediary currency or centralized trusted third party, reducing transaction times between Bitcoin and Ethereum swaps to approximately 15 seconds for a market maker, and could be reduced further with future Layer 2 solutions.
The integration of Large Language Models (LLMs) into autonomous robotic agents for conducting online transactions poses significant cybersecurity challenges. This study aims to enforce robust cybersecurity constraints to mitigate the risks associated with data breaches, transaction fraud, and system manipulation. The background focuses on the rise of LLM-driven robotic systems in e-commerce, finance, and service industries, alongside the vulnerabilities they introduce. A novel security architecture combining blockchain technology with multi-factor authentication (MFA) and real-time anomaly detection was implemented to safeguard transactions. Key performance metrics such as transaction integrity, response time, and breach detection accuracy were evaluated, showing improved security and system performance. The results highlight that the proposed architecture reduced fraudulent transactions by 90%, improved breach detection accuracy to 98%, and ensured secure transaction validation within a latency of 0.05 seconds. These findings emphasize the importance of cybersecurity in the deployment of LLM-driven robotic systems and suggest a framework adaptable to various online platforms.
By drawing from the Technology-Organization-Environment (TOE) theory, this research aims to develop a model to examine the adoption of a blockchain technology based on a survey from 362 manufacturers in Sichuan, China. A structural equation modeling method was adopted to analyze the effects of the TOE approach on the manufacturerâs adoption of blockchain technology. The results indicated that technology, organization, and the environment had positive effects on the manufacturerâs adoption of blockchain technology. Organizational factors are significant antecedents to a manufacturerâs adoption of blockchain technology, followed by technological and environmental factors. Specifically, this research found that environmental factors had a moderating effect and strengthened the influence of organizational factors on the manufacturerâs adoption of blockchain technology. Managerial and theoretical implications from the research findings were discussed to develop blockchain technology in the manufacturing industry.
The stock market is a vital component of the financial sector. Due to the inherent uncertainty and volatility of the stock market, stock price prediction has always been both intriguing and challenging. To improve the accuracy of stock predictions, we construct a model that integrates investor sentiment with Long Short-Term Memory (LSTM) networks. By extracting sentiment data from the âFinancial Postâ and quantifying it with the Vader sentiment lexicon, we add a sentiment index to improve stock price forecasting. We combine sentiment factors with traditional trading indicators, making predictions more accurate. Furthermore, we deploy our system on the blockchain to enhance data security, reduce the risk of malicious attacks, and improve system robustness. This integration of sentiment analysis and blockchain offers a novel approach to stock market predictions, providing secure and reliable decision support for investors and financial institutions. We deploy our system and demonstrate that our system is both efficient and practical. For 312 bytes of stock data, we achieve a latency of 434.42 ms with one node and 565.69 ms with five nodes. For 1700 bytes of sentiment data, we achieve a latency of 1405.25 ms with one node and 1750.25 ms with five nodes.
⢠Blockchain can be used to create token-based inducement systems. ⢠The integration of blockchain supports distributed energy systems and P2P in green energy trading. ⢠Blockchain technology allows transparent and immutable recording of green energy transactions. ⢠Blockchain facilitates automated and efficient trading of renewable energy. ⢠Key trends and influential papers in the field are identified using bibliometric analysis. Blockchain is evolving as a crucial technology in protecting the future outlook of energy systems and global economic competition. As a result of the huge rise in industrial pollution, it has gained extensive consideration from economic establishments, green energy supply organizations, tech designers, governments, and researchers. Stakeholders from various fields identify the potential of blockchain integration with green energy as a tool to transform different activities in the sector, such as reducing the grid's major carbon emissions, freeing cyber theft and generating novelty. Moreover, blockchain system is tamper-proof, transparent, and has the prospect of addressing novel business solutions, mostly when integrated with smart contracts. In this study, 510 documents from 2017 to 2024 were selected and visualized using CiteSpace software and bibliometric approaches to analyze the research field's growth base, hotspot areas, country and their policy implementations, collaborative groups, and evolutionary trends of blockchain base within energy networks. It investigates the existing literature to acknowledge the progress made in the field. The key findings show that basic research on blockchain technology in the energy sector is fast growing with time, showing that integrating blockchain and green energy is an emerging research field. Out of 742 countries and regions, China leads with 89 publications, recording 24.7%, followed by India with 78 publications, accounting for 21.7%, and the United States with 76 publications, accounting for 21.1%. Among them, China's collaborations rely mainly on renewable energy management. Moreover, the practical application cases corresponding to research hotspots are mostly located in developed countries, especially in the United States, the European Union, and Australia. The research gaps in blockchain-based green energy applications are noticed in green certificate trading, micro-grid energy market, technology and policy, energy management, as well as potential trends in energy internet, energy systems, and green power trading. The findings of this paper will assist researchers in gaining a vast knowledge of the present research in the area of blockchain and green energy and identify future research trends in the field. Hence, this will boost the knowledge of energy expansion among energy trading experts, seize possible opportunities, and offer beneficial insights for the government to introduce blockchain advancement and green energy trading policies.
We examine if the day-of-the-week effect is present in Bitcoin return series. The model specification in use accounts for conditional heteroscedasticity, which is captured in the form of a stochastic volatility process that allows for periodic time-varying parameters. We find periodicity in Bitcoin returns, which is evidence against the market efficiency of Bitcoin.
Huan Margana Ritonga, Zara Yunizar, Hafizh Al Kautsar Aidilof
Cryptocurrency has become one of the most intriguing topics in finance and technology in recent years. With the growing prominence of Bitcoin, the rise of altcoins (alternative cryptocurrencies) also demonstrates significant potential within the cryptocurrency market. Altcoins, which include all cryptocurrencies other than Bitcoin, offer diverse functionalities and use cases, ranging from smart contracts to decentralized finance (DeFi) applications. This thesis identifies the altcoin options with the best investment opportunities and the highest growth potential. The study employs the Preference Selection Index (PSI) method, a multi-criteria decision-making approach that evaluates alternatives based on specific preferences and criteria. This method is particularly suitable for assessing complex investment decisions involving multiple variables, such as market capitalization, technological innovation, and utility. By applying PSI, investors can decide which altcoins will likely yield substantial returns. A web-based platform has been developed as part of this research to simplify selecting promising altcoins. This platform enables users to evaluate options based on predefined criteria, such as market trends, project objectives, and development team credibility. The accessibility of this tool empowers usersâwhether novice or experienced investorsâto navigate the dynamic cryptocurrency market more effectively. Altcoins provide a unique opportunity for diversification in investment portfolios. Unlike Bitcoin, which is often viewed as a store of value, many altcoins are designed with specific purposes and innovative features. For instance, Ethereum introduced smart contracts that revolutionized decentralized applications, while other altcoins focus on scalability or niche markets like the Internet of Things (IoT). However, investing in altcoins also comes with challenges like high market volatility, security risks, and regulatory uncertainties. Therefore, thorough research and strategic planning are essential for minimizing risks while maximizing returns in this rapidly evolving sector.
Purpose: This research is to understand Bitcoin in the perspective of contemporary muamalah fiqh, find out how contemporary scholars understand bitcoin and analyze whether it is permissible or not from the perspective of contemporary muamalah fiqh. Design/methodology/approach: This research method is included in the quantitative category with a descriptive approach process, where the data collection technique relies on references in the library method as the main source. In other words, the data collection method is obtained from literature, such as articles, online media, books and other sources. Findings: : The results of this research show that bitcoin as an investment is not permitted because it contains gharar and maysir, and is not recognized as an official medium of exchange. The Indonesian government also does not support bitcoin as an official currency and considers it illegal under the Bank Indonesia Law. Research implications: From the results of this research, it is known that the development of Bitcoin in the Contemporary Prefective Fiqh of Muamalah, namely cryptocurrency, whether Bitcoin or other related cryptocurrencies, is still not accepted in Islamic law. and it could be said that it has not been legally and legitimately accepted in Indonesia.
Abstract Contractual relationships between buyers and sellers can be disrupted by unanticipated shocks to attributes of the exchanged good or service; in manufacturing, such relationships often involve one buyer of components or intermediate goods and many potential sellers. We study the buyerâs selection of a seller given the option to initially agree on a smart contract which, in the advent of such unanticipated shocks, automatically adjusts the exchange price. Our benchmark analysis focuses on the case where a positive potential shock raises attribute values for both contracting parties, implying that the seller benefits more than the buyer from executing the original contract at the agreed exchange price. Taking the perspective of the buyer, we vary the shock and utility parameters to arrive at conclusions regarding the determinants of smart contract dominance in random buyer-seller matches. One of the key issues analyzed in this paper is the possibility that after the potential shock, another seller might be better and a buyer who anticipates this might be led to select a different seller. For the case of the Nash bargaining-solution, we further investigate the impact of increasing the number of utility-generating attributes on these switch rates.
Penelitian ini bertujuan untuk menguji pengaruh faktor-faktor yang mempengaruhi Keputusan Investasi Cryptocurrency pada kaum Millenial di Kota Batam. Faktor-faktor tersebut antara lain Overconfidence, Risk Tolerance, dan Financial Experience. Pendekatan yang digunakan dalam penelitian ini adalah kuantitatif, dengan data primer yang diperoleh melalui penyebaran kuesioner. Populasi dalam penelitian ini berjumlah 443.180, dan sampel yang diambil sebanyak 100 orang dengan menggunakan rumus Slovin dengan tingkat kesalahan 10%. Penelitian ini menggunakan probability sampling dengan metode random sampling. Teknik analisis yang digunakan meliputi analisis deskriptif, uji instrumen, uji asumsi klasik, uji regresi linier berganda, dan uji hipotesis, dengan pengolahan data melalui SPSS versi 25. Hasil penelitian menunjukkan bahwa Overconfidence, Risk Tolerance, dan Financial Experience berpengaruh signifikan terhadap Keputusan Investasi Cryptocurrency. Kesimpulannya, H1 diterima, H2 diterima, H3 diterima, H4 diterima.Kata Kunci: overconfidence, risk tolerance, financial experience, keputusan investasi cryptocurrency.
The integration of Zero-Trust Architecture (ZTA) and Blockchain-based Security Models in IoT-driven industrial power electronics systems has emerged as a transformative approach to mitigating cyber threats and ensuring robust access control. Traditional security mechanisms, which rely on perimeter-based defenses, are increasingly ineffective against advanced persistent threats (APTs), insider attacks, and lateral movement techniques within industrial IoT (IIoT) environments. Zero-Trust security enforces continuous verification, least-privilege access, and micro-segmentation, ensuring that no device or user was inherently trusted. Implementing ZTA in resource-constrained IoT ecosystems presents significant challenges related to computational overhead, authentication latency, and secure data transmission. To address these limitations, blockchain technology enhances decentralized identity management, immutable access logs, and tamper-resistant security frameworks, fortifying Zero-Trust-based access control. Privacy-preserving cryptographic techniques, including zero-knowledge proofs (ZKPs) and homomorphic encryption, safeguard sensitive industrial data while maintaining compliance with evolving regulatory frameworks. AI-driven anomaly detection models reinforce continuous authentication and behavior-based threat monitoring, enabling proactive defense mechanisms against zero-day exploits and sophisticated cyber intrusions. This chapter presents a comprehensive analysis of Zero-Trust implementation models for IIoT systems, highlighting the role of secure communication protocols, distributed ledger-based identity verification, and adaptive security automation. The integration of blockchain-enabled access control and AI-powered real-time security analytics ensures a resilient security posture for industrial power electronics networks, mitigating risks associated with unauthorized access, data breaches, and operational disruptions. The proposed framework enhances scalability, privacy, and computational efficiency, paving the way for next-generation cybersecure industrial ecosystems.
The integration of Internet of Things (IoT) devices in healthcare has enhanced medical efficiency but poses challenges such as data privacy risks and internal abuse. Traditional IoT data access frameworks suffer from centralization, limited scalability, and static permission controls. To address these issues, we propose MedAccessX, a blockchain-based access control framework combining attribute-based access control (ABAC) and role-based access control (RBAC). MedAccessX utilizes four types of smart contracts: a user management contract (UMC) for managing user operations, a medical data management contract (MDMC) for handling data, a policy contract (PC) for managing access rights, and an access control contract (ACC) for enforcing permissions and facilitating data sharing. Our evaluation, conducted on a private Ethereum blockchain network with multiple nodes, assesses security, deployment cost, gas consumption, throughput, and response time. Comparative analysis demonstrates that MedAccessX achieves lower deployment costs and higher throughput, outperforming existing solutions.
The integration of Artificial Intelligence (AI) in finance has significantly transformed various aspects of the industry, from algorithmic trading and risk management to regulatory compliance and decentralized finance (DeFi). AI-driven models enhance market prediction accuracy, automate trading strategies, and improve fraud detection, thereby increasing efficiency and reducing financial risks. Moreover, AI-powered robo-advisors and credit scoring systems contribute to financial inclusion by offering personalized and data-driven services. Despite these advancements, challenges such as AI explainability, data privacy concerns, algorithmic bias, and regulatory constraints remain critical research areas. Additionally, emerging trends, including quantum computing, AI-enhanced DeFi, and privacy-preserving machine learning, are expected to further shape the future of AI applications in finance. This paper provides a comprehensive review of AI-driven innovations in financial markets, banking services, and regulatory compliance while discussing ongoing challenges and future research directions.
This study presents an advanced adaptive trading framework that integrates Deep Reinforcement Learning (DRL) with the Iterative Model Combining Algorithm (IMCA) to overcome the critical limitations of static ensemble methods in global portfolio optimization. Using a diverse cross-market dataset of 39 stocks from the US, Australia, Europe, Thailand, and one cryptocurrency (BTC-USD), the research rigorously evaluates modelsâ adaptability under volatile market conditions. Volatile market conditionsâsuch as COVID-19, SVB crisis, and the 2022 crypto crashâare captured via volatility metrics (e.g., drawdown), with DRL models like PPO/TD3 adapting through dynamic reward signals. This cross-asset integration is particularly critical, as it captures the complex dynamics and correlations between traditional financial markets and emerging digital assets. Although DRL models like PPO and TD3 outperform traditional strategies, they remain vulnerable to market drawdowns and high volatility. IMCA significantly surpasses these models, achieving the highest cumulative return of 29.52% and a superior Sharpe ratio of 0.829 by dynamically recalibrating model weights in response to real-time market dynamics. This study addresses a substantial research gap, highlighting the failure of traditional ensemble modelsâreliant on static weightingsâto adapt to evolving financial conditions, resulting in suboptimal risk-adjusted returns. IMCA offers a dynamic, data-driven approach that continuously optimizes portfolio strategies across fluctuating market regimes, demonstrating its scalability and robustness across diverse asset classes and regional markets, and providing an empirical framework for adaptive portfolio management. Policy recommendations underscore the need for financial institutions to adopt AI-driven adaptive models like IMCA to enhance portfolio resilience, profitability, and responsiveness in uncertain markets.
Federated learning (FL) is an emerging paradigm that enables multiple clients to collaboratively train a machine learning (ML) model without the need to exchange their raw data. However, it relies on a centralized authority to coordinate participantsâ activities. This not only interrupts the entire training task in case of a single point of failure, but also lacks an effective regulatory mechanism to prevent malicious behavior. Although blockchain, with its decentralized architecture and data immutability, has significantly advanced the development of FL, it still struggles to withstand poisoning attacks and faces limitations in computational scalability. We propose Zkfhed, a verifiable and scalable FL system that overcomes the limitations of blockchain-based FL in poison attacks and computational scalability. First, we propose a two-stage audit scheme based on zero-knowledge proofs (ZKPs), which verifies that the training data are extracted from trusted organizations and that computations on the data exactly follow the specified training protocols. Second, we propose a homomorphic encryption delegation learning (HEDL), based on fully homomorphic encryption (FHE). It is capable of outsourcing complex computing to external computing resources without sacrificing the client's data privacy. Final, extensive experiments on real-world datasets demonstrate that Zkfhed can effectively identify malicious clients and is highly efficient and scalable in terms of online time and communication efficiency.
With the development of communication infrastructure and the popularity of smart devices, e-commerce is presenting in more diverse forms and attracting the attention of more and more users. Since e-commerce transactions usually involve sensitive information of a large number of users, privacy and security have become increasingly important issues. Despite certain advantages (e.g., trading security), the privacy protection capability and efficiency of blockchain is still limited by some key factors, especially of its architecture. In this paper, we propose a blockchain-based privacy protection system named PBTMS that integrates zero-knowledge proofs, hybrid encryption, and Pedersen commitments as foundational mechanisms to ensure robust privacy protection for transaction data and user information. To achieve secure, reliable, and efficient e-commerce transactions, the PBTMS employs blockchain technology and consensus mechanisms to enable distributed storage, thereby mitigating single points of failure and addressing the risks posed by malicious nodes. Moreover, by integrating on-chain storage with off-chain computation, the system substantially reduces blockchain-related overheads, including processing time, gas consumption, and storage costs. This design establishes the PBTMS as a highly adaptable and efficient system for the evolving requirements of secure and privacy-preserving e-commerce platforms. Theoretical analysis and experimental validation demonstrate that PBTMS reduces decryption and authentication times by 79.2% and 52.6%, respectively, while cutting encrypted data size by 52.5% and overall gas consumption by 55.4%, outperforming state-of-the-art solutions. These results indicate that PBTMS is a reliable and efficient system for secure e-commerce transaction platforms and provides a novel approach to enhancing privacy protection in e-commerce.
Sami Ben Jabeur, Zouhaier Dhifaoui, Yassine Bakkar, Houssein Ballouk
This study provides evidence on the role of the quality of political signals in predicting six major cryptocurrency asset classes. Including communications from the U.S. presidential election in 2024, we find that political news affects cryptocurrency returns in the short-term (from ⟠2 to ⟠4 months). For most cryptoassets, text sentiment measures demonstrate superior predictive performance compared to historical cryptocurrency time series in out-of-sample forecasts. ⢠Analyzes the effect of political signals on cryptocurrency returns. ⢠Political news influences cryptocurrency returns in the short term. ⢠Political signals enhances the accuracy of Bitcoin return forecasts.
The article examines the definition of ÂŤcryptocurrency,Âť its legal status, and prospects for regulation in Ukraine. The authors analyze contemporary approaches to understanding cryptocurrency as a digital asset, considering it either as a new form of money or as an object of civil rights. Particular attention is paid to the provisions of the Law of Ukraine ÂŤOn Virtual Assets,Âť adopted on February 17, 2022, and its significance in creating the legal foundation for cryptocurrency market regulation. However, it is emphasized that this law has not yet come into force due to the absence of corresponding amendments to tax legislation, complicating the legalization of cryptocurrency transactions. The distinction between ÂŤvirtual assetsÂť and ÂŤcryptocurrenciesÂť is discussed, highlighting key limitations of existing legislation, particularly the prohibition on using virtual assets as a payment method in Ukraine. The article outlines issues such as the lack of a transparent regulatory environment and a taxation system, which hinder the development of the cryptocurrency market, reduce its investment appeal, and create risks for market participants. The article also analyzes international cryptocurrency regulation experiences, particularly in the United States, Canada, Japan, and the European Union. Special attention is devoted to the European regulation Markets in Crypto Assets (MiCA), which could serve as a foundation for developing a unified regulatory framework in Ukraine. The authors stress the importance of harmonizing Ukrainian legislation with European standards within the framework of European integration. The potential benefits of cryptocurrency legalization are highlighted, including attracting foreign investments, developing financial technologies, reducing the shadow economy, strengthening consumer protection, and creating new markets. Specific recommendations are provided to improve legislation, such as implementing transparent regulatory mechanisms, taxation, investor protection, and ensuring cybersecurity. This article is a significant contribution to the study of the prospects for the development of the cryptocurrency market in Ukraine, outlining the challenges and opportunities for integrating Ukraineâs financial system into the international space through the adoption of MiCA standards.
Detecting fraudulent activities such as Ponzi schemes within smart contract transactions is a critical challenge in decentralized finance. Existing methods often fail to capture the heterogeneous, multi-faceted nature of blockchain data, and many graph-based models overlook the contextual patterns that are vital for effective anomaly detection. In this paper, we propose MVCG-SPS, a Multi-View Contrastive Graph Neural Network designed to address these limitations. Our approach incorporates three key innovations: (1) Meta-Path-Based View Construction, which constructs multiple views of the data using meta-paths to capture different semantic relationships; (2) Reinforcement-Learning-Driven Multi-View Aggregation, which adaptively combines features from multiple views by optimizing aggregation weights through reinforcement learning; and (3) Multi-Scale Contrastive Learning, which aligns embeddings both within and across views to enhance representation robustness and improve anomaly detection performance. By leveraging a multi-view strategy, MVCG-SPS effectively integrates diverse perspectives to detect complex fraudulent behaviors in blockchain ecosystems. Extensive experiments on real-world Ethereum datasets demonstrated that MVCG-SPS consistently outperformed state-of-the-art baselines across multiple metrics, including F1 Score, AUPRC, and Rec@K. Our work provides a new direction for multi-view graph-based anomaly detection and offers valuable insights for improving security in decentralized financial systems.
ABSTRACT This study examines how task assignment mechanisms affect the participation of workers on decentralized blockchains. In developing the theory, I highlight that blockchain represents a distinct organizational form for coordinating operations under a highly decentralized structure, in which the essential tasks of system infrastructure maintenance are assigned to thirdâparty crowd workers through the unique governance mechanism of consensus protocol. I specifically focus on two widely adopted consensus protocols in the context of cryptocurrency, namely, proofâofâwork (PoW), which assigns tasks that sustain the blockchain system operation based on workers' investments in computing power, and proofâofâstake (PoS), which assigns these tasks based on workers' investments in the native cryptocurrency as stakes. I argue that compared with PoW, PoS increases worker participation and task decentralization because the investment requirement of task participation in the form of blockchain native assets reduces workers' transaction costs in task contracting and their tendencies for hyperâcompetition. My empirical analysis leverages a natural experiment on Ethereum, namely, the âMergeâ event on September 15, 2022, in which the blockchain changed the assignment rules by switching the consensus protocol from PoW to PoS. The results under a differenceâinâdifferences research design confirm my arguments.
Cryptocurrency represents a form of asset that has arisen from the progress of financial technology, presenting significant prospects for scholarly investigations. The ability to anticipate cryptocurrency prices with extreme accuracy is very desirable to researchers and investors. However, time-series data presents significant challenges due to the nonlinear nature of the cryptocurrency market, complicating precise price predictions. Several studies have explored cryptocurrency price prediction using various deep learning (DL) algorithms. Three leading cryptocurrencies, determined by market capitalization, Ethereum (ETH), Bitcoin (BTC), and Litecoin (LTC), are examined for exchange rate predictions in this study. Two categories of recurrent neural networks (RNNs), specifically long short-term memory (LSTM) and gated recurrent unit (GRU), are employed. Four performance metrics are selected to evaluate the prediction accuracy namely mean squared error (MSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean squared error (RMSE) for three cryptocurrencies which demonstrates that GRU model outperforms LSTM. The GRU model was implemented as a two-layer deep learning network, optimized using the Adam optimizer with a dropout rate of 0.2 to prevent overfitting. The model was trained using normalized historical price data sourced from CryptoDataDownload, with an 80:20 train-test split. In this work, GRU qualifies as the best algorithm for developing a cryptocurrency price prediction model. MAPE values for BTC, LTC and ETH are 0.03540, 0.08703 and 0.04415, respectively, which indicate that GRU offers the most accurate forecasts as compared to LSTM. These prediction models are valuable for traders and investors, offering accurate cryptocurrency price predictions. Future studies should also consider additional variables, such as social media trends and trade volumes that may impact cryptocurrency pricing.
Mohammed Ababneh, Kartick Kolachala, Roopa Vishwanathan
Payment channel networks (PCNs) are a promising solution to address blockchain scalability and throughput challenges, However, the security of PCNs and their vulnerability to attacks are not sufficiently studied. In this paper, we introduce SCOOP, a framework that includes two novel congestion attacks on PCNs. These attacks consider the minimum transferable amount along a path (path capacity) and the number of channels involved (path length), formulated as linear optimization problems. The first attack allocates the attacker's budget to achieve a specific congestion threshold, while the second maximizes congestion under budget constraints. Simulation results show the effectiveness of the proposed attack formulations in comparison to other attack strategies. Specifically, the results indicate that the first attack provides around a 40\% improvement in congestion performance, while the second attack offers approximately a 50\% improvement in comparison to the state-of-the-art. Moreover, in terms of payment to congestion efficiency, the first attack is about 60\% more efficient, and the second attack is around 90\% more efficient in comparison to state-of-the-art