Purpose This paper aims to delve into the intricate dynamics of the Bitcoin market, combining established financial theories with innovative methodologies to assess market efficiency and identify anomalies. Design/methodology/approach The paper investigates the efficiency of the Bitcoin market through a diverse set of lenses, using statistical methods such as linear and rank correlations, mean absolute error, mean squared error and introducing a unique copula-based approach for modeling dependence structures. The authors explore the weak form of informational market efficiency, focusing on the period before and after 2014. Findings Notable findings from this study include evidence of partial inefficiency, the emergence of anomalies, and the presence of predictability, challenging the assumption of a pure martingale. Structured into sections reviewing relevant literature, outlining this empirical methodology, presenting robust empirical results and concluding with insights and implications, this paper contributes to a deeper understanding of Bitcoin’s market behavior. Originality/value Despite the extensive literature on market efficiency, the Bitcoin market remains relatively unexplored. This study addresses this gap, offering a nuanced analysis that goes beyond traditional measures. This work emphasizes the relevance of adopting innovative approaches to assess market efficiency in a rapidly evolving financial landscape.
This study investigates the safe-haven and diversification roles of gold and Bitcoin in financial markets from 2015 to 2025. With rising economic uncertainties, the need for reliable safe-haven assets has become critical. Gold has historically provided stability during crises, whereas Bitcoin's volatile nature raises questions about its reliability as a safe haven. Through empirical analysis, including GARCH models and quantile regression, the research evaluates the performance of both assets during market stress. Findings indicate that gold consistently outperforms Bitcoin in terms of downside protection, confirming its status as a traditional safe-haven asset. Conversely, Bitcoin offers potential diversification benefits, enhancing portfolio performance when combined with gold. The results support the notion that integrating both assets can lead to improved risk-adjusted returns, making a dual-asset investment strategy a practical approach for investors navigating market uncertainties.
The rapid adoption of Internet of Things (IoT) in Healthcare has significantly enhanced real-time patient monitoring and decision making. However, security and privacy still remain the major concern due to sensitive medical data of patients especially on low-power IoT devices. Traditional authentication schemes like Zero Knowledge Proof (ZKP) and Elliptic Curve Cryptography (ECC) often struggle with efficiency in resource-constraint environments due to their computational overhead. In order to address these challenges, we propose a Neural-Based Hybrid and Adaptive Framework that combines Schnorr ZKP with Kyber-based key encapsulation, using a neural network to dynamically select Kyber variants (512, 768, 1024) based on device parameters (type, authentication time, transmission time) to balance security and efficiency for low-power IoT devices. Extensive experiments validated robust security against replay and spoofing attacks, achieving authentication success for legitimate clients and zero attack successes. Furthermore, our proposed framework outperforms traditional Kyber1024 and ZKP/ECC based authentication schemes in terms of authentication time and computational overhead making it robust and scalable solution for sensitive and resource-limited environments like HealthCare IoT systems. • Design a novel hybrid authentication framework that integrates ZKP and Kyber PQC (Post Quantum Cryptography) to ensure secure and efficient authentication for IoT healthcare devices. • Utilize Neural Network to intelligently select the most appropriate Kyber variant based on threat level and computational efficiency. • Provide comprehensive experimental analysis comparing the proposed hybrid and adaptive framework with traditional ZKP, ECC and static Kyber implementations.
Reilly Smethurst, Orestis Papageorgiou, Ben Egliston
Blockchain-tokenised media is kitsch. We examined OpenSea’s top 50 collections of non-fungible tokens (NFTs) as well as the first two NFTs acquired by New York’s Museum of Modern Art (MoMA). We concomitantly developed two concepts: oppositional kitsch, and historically informed kitsch. OpenSea’s profile picture collections exemplify oppositional kitsch: they are described by their creators as anti-normal, degenerate or animalistic. CryptoPunks and Bored Apes are the best-known examples. Historically informed kitsch is, by contrast, pleasant and reassuring. MoMA’s first two NFTs exemplify historically informed kitsch: they are produced by artificial intelligence (AI) models that rely on historical data. For Unsupervised – Machine Hallucinations – MoMA , Refik Anadol trained an AI model with images from MoMA’s GitHub archive. The Unsupervised NFTs are mementos of individuals’ encounters with the work at MoMA. For 3FACE , Ian Cheng created an AI model that draws on blockchain transaction histories. The AI model generates tokenised portraits of individuals based on their transactions. Oppositional kitsch and historically informed kitsch both valorise the individual consumer. OpenSea’s oppositional kitsch lets consumers identify with cartoon figures like CryptoPunks and Bored Apes that are marketed as avatars (alter-egos) and profile pictures. MoMA’s historically informed kitsch sells mementos of individuals’ experiences and portraits that are based on individuals’ consumption choices. Our conception of blockchain-tokenised media as kitsch is primarily informed by the philosophers Alain Badiou and Thorsten Botz-Bornstein as well as the media theorist Jean Baudrillard. These three thinkers treat kitsch as a category of sophistic, liberal-cum-libertarian culture.
Alexia Marcu, Flavia Antăluţe, Adrian Alexandrescu
In response to the growing demand for secure, transparent, and adaptive digital education systems, this paper presents a novel decentralized platform that redefines how learning outcomes are assessed, stored, and certified. The proposed architecture integrates blockchain technology, dynamic non-fungible tokens (dNFTs), and artificial intelligence to establish a verifiable and learner-centric educational ecosystem. Decentralized storage is handled via InterPlanetary File System (IPFS), secured through hybrid encryption and controlled access, ensuring that sensitive data such as assessments and performance records remain both confidential and tamper-proof.A distinctive feature of the platform is the use of dynamic dNFTs to represent and continuously update each learner’s academic progress. Unlike static certificates, these credentials evolve as students complete assessments and advance through course material, offering a transparent and verifiable record of learning achievements anchored on the blockchain. Each dNFT encodes metadata such as course names, skill levels, and timestamps, ensuring long-term integrity and resistance to tampering. Complemented by an AI module for personalized test generation, this model replaces traditional certification with an adaptive, decentralized alternative that enhances trust, autonomy, and credential portability across educational and professional domains.
Zilga Heritiana Randriamiarison, Hajarisena Razafimahatratra, Nicolas Raft Razafindrakoto, Yassine Rhazali
A smart contract is a program deployed on a blockchain network and becomes immutable once deployed. Reentrancy bugs are among the most significant vulnerabilities in blockchain technology. Numerous approaches have been proposed to detect and analyze them. However, minimizing reentrancy errors in smart contracts remains a challenge. The aim of this paper is to optimize the handling of reentrancy bugs in smart contracts across different versions of Solidity. It also proposes a new method for syntactic and lexical code detection. Our approach is based on static analysis, and the tool can detect different versions of smart contract code. We used regex to identify external calls in the contract and Control Flow Graph (CFG) to identify the components of the code. A detection algorithm was developed to identify reentrancy vulnerabilities. This approach enhances contract reliability and reduces risk prior to deployment. Our method has been evaluated using True Positive Rate (TPR) and False Positive Rate (FPR) metrics. We tested it on the SmartBugs benchmark suite and contracts from Etherscan. The contracts analyzed include two solidity versions: 0.4.x and 0.8.x. Thanks to the integration of multiple tools, our solution supports testing across different solidity versions.
Flavia Antăluţe, Alexia Marcu, Adrian Alexandrescu
EduPlay is an interactive educational platform that reimagines traditional homework as a personalized, engaging, and secure experience for middle school students. Combining blockchain technology, gamification, and decentralized storage via IPFS (InterPlanetary File System), EduPlay ensures transparency, authorship traceability, and student motivation. Learners complete tasks using an intuitive visual canvas, and in collaborative projects, each user’s contribution is automatically recorded and verifiably linked to their identity on the blockchain.A central feature of EduPlay is its use NFTs (Non-Fungible Tokens) as immutable certificates of achievement. Blockchain is also used for tracking collectible cards within a trading system. Students are encouraged to build collections, trade cards with peers, and unlock learning incentives, making academic progress tangible and engaging.Teachers can create and evaluate assignments with customizable templates and receive real-time insights into student performance. Parents gain visibility into their child’s progress through a dedicated dashboard. EduPlay promotes creativity, collaboration, and transparent learning outcomes in a gamified, student-centered environment.
Jinho Cha, Young‐Chul Kim, Junyeol Ryu, Sangjun Park · 6 authors
This study develops a strategic procurement framework integrating blockchain-based smart contracts with bounded demand variability modeled through a truncated normal distribution. While existing research emphasizes the technical feasibility of smart contracts, the operational and economic implications of adoption under moderate uncertainty remain underexplored. We propose a multi-supplier model in which a centralized retailer jointly determines the optimal smart contract adoption intensity and supplier allocation decisions. The formulation endogenizes adoption costs, supplier digital readiness, and inventory penalties to capture realistic trade-offs among efficiency, sustainability, and profitability. Analytical results establish concavity and provide closed-form comparative statics for adoption thresholds and procurement quantities. Extensive numerical experiments demonstrate that moderate demand variability supports partial adoption strategies, whereas excessive investment in digital infrastructure can reduce overall profitability. Dynamic simulations further reveal how adaptive learning and declining implementation costs progressively enhance adoption intensity and supply chain performance. The findings provide theoretical and managerial insights for balancing digital transformation, resilience, and sustainability objectives in smart contract-enabled procurement.
In the contemporary online interaction, digital iden- tity is central, but most systems follow a centralized provider like Google or Facebook. Although convenient, these models pose ma- jor risks to data breach, surveillance, and single point of failure. The proposed paper proposes a privacy-sensitive decentralized identity verification system that uses Zero-Knowledge Proofs (ZKPs) to allow users to make it through claims (e.g., age, citizen- ship, or enrollment) without any personal data being provided, thereby solving the challenges outlined in the paper. Our architecture integrates verifiable credentials, zero-knowledge-SNARKs and an issuer trust registry that is maintained on blockchain smart contracts to guarantee trustless verification and eliminate dependence on centralized authorities. Its system gives its users full control over credentials, allows reuse across applications, and does not expose data.A proof-of-concept implementation has shown the approach to be feasible with Circom and SnarkJS to generate proof, Solidity smart contracts to verify them, and a user interface implemented in React. Results of the evaluations showed that determination of the verification latency is low, the overhead to generate proofs is moderate, and no privacy leakage occurs. It can be used in potential applications such as education, e-governance, healthcare, finance, and online voting.
Ziyang Liu, Kenneth MacKenzie, Roman Kireev, Michael Peyton Jones · 6 authors
The Cardano blockchain is the first to use proof of stake, offers native support for multiple currencies and is evolving toward a distributed governance model. It supports smart contracts through Plutus, a language based on System Fω with recursion. About half a dozen languages compile into Plutus, the first of which is Plinth (formerly Plutus Tx) — a language that reuses a subset of the Haskell syntax, and has been in commercial use since 2021.
Zero-knowledge proof (ZKP) applications require translating high-level programs into arithmetic circuits–a process that demands both correctness and efficiency. While recent DSLs improve usability, they often yield suboptimal circuits, and hand-optimized implementations remain difficult to construct and verify. We present Tabby, a synthesis-aided compiler that automates the generation of high-performance ZK circuits from highlevel code. Tabby introduces a domain-specific intermediate representation designed for symbolic reasoning and applies sketch-based program synthesis to derive optimized low-level implementations. By decomposing programs into reusable components and verifying semantic equivalence via SMT-based reasoning, Tabby ensures correctness while achieving substantial performance improvements. We evaluate Tabby on a suite of real-world ZKP applications and demonstrate significant reductions in proof generation time and circuit size against mainstream ZK compilers.
Abstract Artificial intelligence (AI) systems are rapidly approaching capabilities that require an increasing level of human control. Existing AI alignment techniques remain opaque, model-specific, and vulnerable in human-level AI, or post-quantum scenarios. To address these issues, this paper proposes a novel AI alignment system architecture in which AI alignment rules are encoded as immutable smart contracts on a blockchain. The blockchain, in turn, is governed by a Proof of Personhood (PoP) consensus mechanism that only admits human agents to the rule validation processes. To protect the privacy of human agents in the identity verification process, the proposed AI alignment system facilitates techniques such as key derivation functions and asymmetric encryption of biometric data. In addition, this system also utilizes blockchain-based decentralized identity (DID) and zero-knowledge proofs (ZKPs). To ensure privacy in post-quantum scenarios, biometric data are linked to zk-STARKs. The proposed AI alignment system is formally described to capture human and AI agents, verification, authentication, and Sybil resistance. The AI shield, a reactive system that prevents unsafe actions by an AI agent that would violate predetermined conditions, enforces the blockchain-based AI alignment rules in real-time, independently of the underlying AI model. Thus, the contribution of this paper is a conceptual framework for the implementation of blockchain technology that utilizes a PoP-based consensus mechanism and zk-STARKs to foster privacy-friendly societal involvement and public auditability of AI developments, providing a democratically governed AI alignment layer applicable to current and future AI models, including those in a post-quantum era.
Ejielo Ogbuefi, Stephen Ehilenomen Aifuwa, Jennifer Olatunde-Thorpe, David Akokodaripon
Resilience in critical infrastructures (CIs) has emerged as a pressing global concern, as societies become increasingly dependent on tightly interconnected systems that support communication, energy, finance, and healthcare. These infrastructures, once considered largely independent, now operate within a convergent ecosystem where disruptions in one domain can propagate rapidly across others, leading to cascading failures with severe societal and economic consequences. Conceptual frameworks addressing resilience in such interdependent systems emphasize the need to move beyond traditional robustness toward adaptive, absorptive, and restorative capacities that account for dynamic risks, systemic vulnerabilities, and emergent behaviors. The convergence of communication technologies with energy, financial, and healthcare services introduces both opportunities and challenges. While digital integration enhances efficiency, situational awareness, and service delivery, it also amplifies exposure to cyber threats, systemic shocks, and supply chain fragilities. For instance, a cyberattack on a power grid can simultaneously disrupt healthcare delivery and financial transactions, while communication failures may impede crisis coordination. To address these risks, resilience frameworks increasingly adopt network-centric, socio-technical, and complex adaptive systems perspectives, highlighting interdependencies and the need for multi-level governance. Key strategies include embedding redundancy and decentralization in communication systems, deploying microgrids and storage in energy infrastructures, integrating distributed ledgers and systemic risk monitoring in finance, and strengthening telemedicine and emergency preparedness in healthcare. At a broader level, resilience planning requires cross-sector interoperability standards, public–private collaboration, and ethical prioritization of vulnerable populations. Emerging tools such as AI-driven predictive analytics and digital twins offer promising avenues for resilience assessment and proactive adaptation. Ultimately, resilience in convergent critical infrastructures demands an integrated, multidisciplinary approach that bridges engineering, policy, and social dimensions. By adopting conceptual frameworks that embrace interdependency, adaptability, and inclusivity, societies can enhance preparedness, mitigate cascading risks, and ensure continuity of vital services under conditions of uncertainty.
Open access
Infrastructure Resilience and Vulnerability Analysis
Abdullah Yousafzai, Muhammad Mohsan Sheeraz, Ganna Pogrebna, Jon Crowcroft · 5 authors
The metaverse is a shared virtual 3D space that combines immersive experiences with applications in gaming, social interactions, commerce, and more. It is rapidly becoming a reality, driven by advances in virtual reality, augmented reality, artificial intelligence, blockchain, and other emerging technologies. Among these, blockchain technology enables secure and decentralized ownership as well as seamless interoperability of virtual assets. Non-fungible tokens ensure verifiable ownership and fraud prevention, while smart contracts facilitate automated peer-to-peer transactions. Blockchain’s security and transparency promote trust and innovation, laying the foundation for a connected and user-driven metaverse ecosystem. In this paper, we explore the role of blockchain technology as a key enabler for the metaverse, providing solutions for decentralization, governance through decentralized autonomous organizations, interoperable mechanisms, digital asset ownership, traceability, auditing, and identity management. We present the key difference between traditional virtual worlds and the metaverse, and why blockchain is preferred over other decentralized technologies for the metaverse. We comprehensively review recent advances in metaverse system architectures, focusing on state-of-the-art solutions and lessons learned. We compare the existing literature based on key parameters; namely, contributions, advantages, limitations, and applications. We present key challenges, including deepfake threats, identity theft and brand infringement risks, mental health risks, digital safety and gambling risks, virtual world laws and regulations, and privacy and data security concerns. We outline future recommendations for enabling a sustainable and user-friendly metaverse ecosystem.
Blockchain technologies have profoundly transformed information systems by providing decentralized infrastructures that enhance transparency, security, and traceability. Ethereum, in particular, supports smart contracts and facilitates the development of decentralized finance (DeFi), non-fungible tokens (NFTs), and Web3 applications. However, its openness also enables illicit activities, including fraud and money laundering, through anonymous wallets. Identifying wallets involved in large transfers or abnormal transactional patterns is therefore critical to ecosystem security. This study proposes an AI-based framework employing XGBoost, LightGBM, and CatBoost to detect suspicious Ethereum wallets, achieving test accuracies between 95.83% and 96.46%. The system provides near real-time predictions for individual or recent wallet addresses using a pre-trained XGBoost model. To improve interpretability, SHAP (SHapley Additive exPlanations) visualizations are integrated, highlighting the contribution of each feature. The results demonstrate the effectiveness of AI-driven methods in monitoring and securing Ethereum transactions against fraudulent activities.
Purpose This paper reviews the application of game theory in finance, focusing on its role in modeling strategic interactions among market participants. It synthesizes classical models such as Nash equilibrium and signaling games while integrating emerging themes including behavioral finance, sustainability-linked decisions, decentralized finance (DeFi) and artificial intelligence (AI)-driven agents. The study aims to highlight how game-theoretic frameworks inform financial decision-making, market design and governance and to identify conceptual gaps and future research directions. Design/methodology/approach The study employs a systematic literature review following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses protocol, complemented by bibliometric mapping using VOSviewer. It analyzes 78 peer-reviewed articles published between 2000 and 2025 across five finance domains: asset pricing, corporate finance, investment strategies, financial markets and behavioral finance. Conceptual frameworks and taxonomies are developed to categorize game-theoretic models by strategic orientation and information structure, offering a structured synthesis of theoretical advancements and practical applications. Findings Game theory enhances understanding of strategic behavior in finance, particularly under conditions of asymmetric information and market complexity. Key findings include the relevance of signaling games in initial public offerings pricing, repeated games in environmental, social and governance commitments and mechanism design in DeFi governance. The review identifies gaps in behavioral integration, empirical validation and modeling of decentralized ecosystems. It proposes future research directions involving multi-agent learning, adaptive mechanism design and sustainability-linked financial strategies. Research limitations/implications The review is limited by its focus on published literature and may exclude emerging models in unpublished or proprietary research. Empirical validation of proposed frameworks remains a future research priority. Practical implications The paper offers actionable insights for regulators, investors and policymakers by applying game-theoretic tools to systemic risk management, portfolio allocation and financial regulation in digitized markets. Originality/value This study provides a novel synthesis of game theory’s evolution in finance, introducing conceptual frameworks that integrate behavioral, technological and sustainability-linked dimensions.
S. Sivakumar S., Navin kumaar S, Gugan I, Ramya S R · 6 authors
The paradigm shift is a transition to Web3 in the manner digital businesses are structured, operated and monetised. Web2 brought about the centralized platforms, scale of infrastructure and revenue through advertising, to e-commerce, social media, finance and entertainment industries. Nevertheless, due to such models, additional serious problems also arose, and these were exploitation of user information, user monopoly and bad ownership. Conversely, Web3 takes advantage of this characteristic of decentralization, blockchain trust, token economies and community-based governance to help to facilitate user sovereignty and open-value distribution. Although Web3 has all these benefits in terms of security, transparency and user-engagement, barriers to adoption have to do with scalability, usability and uncertainty in regulation. The paper will trace back the comparison between the Web2 and Web3 business model, how the business model has been applied in various industries and how the user interface design has contributed to creation of trust and compliance. In addition to that, it describes the possible approaches to transition to the realm of decentralized ecosystems and the solution to the question of sustainable and future-proof business models on the digital platform.
Dynamic trust evaluation in large, rapidly evolving graphs demands models that capture changing relationships, express calibrated confidence, and resist adversarial manipulation. DGTEN (Deep Gaussian-Based Trust Evaluation Network) introduces a unified graph-based framework that does all three by combining uncertainty-aware message passing, expressive temporal modeling, and built-in defenses against trust-targeted attacks. It represents nodes and edges as Gaussian distributions so that both semantic signals and epistemic uncertainty propagate through the graph neural network, enabling risk-aware trust decisions rather than overconfident guesses. To track how trust evolves, it layers hybrid absolute-Gaussian-hourglass positional encoding with Kolmogorov-Arnold network-based unbiased multi-head attention, then applies an ordinary differential equation-based residual learning module to jointly model abrupt shifts and smooth trends. Robust adaptive ensemble coefficient analysis prunes or down-weights suspicious interactions using complementary cosine and Jaccard similarity, curbing reputation laundering, sabotage, and on-off attacks. On two signed Bitcoin trust networks, DGTEN delivers standout gains where it matters most: in single-timeslot prediction on Bitcoin-OTC, it improves MCC by +12.34% over the best dynamic baseline; in the cold-start scenario on Bitcoin-Alpha, it achieves a +25.00% MCC improvement, the largest across all tasks and datasets; while under adversarial on-off attacks, it surpasses the baseline by up to +10.23% MCC. These results endorse the unified DGTEN framework.
Haolin Huang, Basem Suleiman, Ali Anaissi, Muhammad Johan Alibasa
Predicting cryptocurrency prices has become increasingly challenging due to their limited trading history and pronounced price volatility. Similar to traditional stock markets, where investor sentiment is significantly influenced by news and social media interactions, Twitter has recently emerged as a prominent indicator of Bitcoin price movements. This study investigates the influence of notable tweets on Bitcoin price fluctuations. In this paper, we present a method to extract hourly and daily impactful tweets related to Bitcoin by leveraging the Twitter network's topology. Furthermore, we propose a Bitcoin price prediction approach that consists of (a) a Twitter sentiment index model, constructed using data from influential tweets, and (b) a time-series XGBoosting model utilising Bitcoin price features derived from historical price data. Through an experimental evaluation, conducted on a substantial dataset comprising 1.8 million tweets, 400k Twitter users, and two months of Bitcoin price data, our model demonstrated superior performance, achieving a MAPE of 0.56%, an R-Square value of 0.99, a Pearson Correlation Coefficient of 0.99, and a Direction Accuracy of 92.06%. Based on the feature importance analysis of our model, we identify that the sentiment index and Bitcoin trade volume wield significant influence over Bitcoin price dynamics. The two-month time range may limit generalization to other market conditions.
The evolution of 5G and emerging 6G networks has introduced unprecedented opportunities for connectivity, but also expanded the attack surface for Distributed Denial of Service (DDoS) amplification attacks. Service-Based Architecture (SBA), network slicing, and massive IoT (mMTC) environments create new vectors for reflection and amplification, making conventional defenses inadequate. This paper proposes a novel layered defense framework that integrates edge filtering, AI-driven anomaly detection, slice isolation, cloud scrubbing, and quantum-safe cryptography to mitigate DDoS amplification attacks in 5G/6G environments. The framework is theoretically modeled through equations for amplification, mitigation efficiency, resilience, and defense cost, and evaluated experimentally using simulated signaling floods, IoT-driven amplification, slice-targeted floods, and hybrid attacks. Performance was measured using detection rate, false alarm rate, service availability, resilience score, and resource overhead. Two algorithms—pseudonymous authentication with zero-knowledge proof (ZKP) and layered mitigation orchestration—were implemented to operationalize the defense strategy. The results demonstrate that the proposed framework achieves a detection accuracy of 95–97%, reduces false positives to 2%, and maintains a service availability of over 85% under prolonged amplification attacks. It scales efficiently in scenarios with up to 10,000 simulated IoT devices, retaining 70–80% throughput, and maintains URLLC latency below 10 ms, outperforming baseline defenses (firewalls, scrubbing, and AI-only) and state-of-the-art defenses from the literature. These findings validate the framework as a scalable, efficient, and future-ready solution for mitigating amplification attacks in 5G/6G networks, with strong alignment with 3GPP, GSMA, and NIST post-quantum standards.
Open access
Advanced Malware Detection Techniques
Network Security and Intrusion Detection
Physical Unclonable Functions (PUFs) and Hardware Security
The banking industry is undergoing a profound transformation driven by digital technologies. Cloud computing, mobile banking, open banking application programming interfaces (APIs), and blockchain are reshaping how financial services are delivered and consumed. While these innovations offer significant benefits, such as improved customer experience, operational efficiency, and new revenue streams, they also introduce complex cybersecurity challenges. In a cloud-first and mobile-first world, banks must navigate a rapidly evolving threat landscape where cybercriminals are increasingly targeting digital platforms, APIs, and emerging technologies like decentralized finance (DeFi).
Cryptocurrency markets are highly volatile, posing significant challenges for accurate price prediction. Solana (SOL), one of the largest cryptocurrencies by market capitalization, experiences sharp fluctuations that limit the effectiveness of traditional linear models such as Autoregressive Integrated Moving Average (ARIMA) and Generalized Autoregressive Conditional Heteroskedasticity (GARCH). To address this, the present study evaluates twelve Long ShortTerm Memory (LSTM) architecture variants, including vanilla LSTM, stacked LSTM, bidirectional LSTM, and hybrid models with attention and dropout mechanisms, for forecasting daily closing prices of the SOL/USD pair. Five years of OHLCV data from Coinbase were used, with an $80 / 10 / 10$ split for training, validation, and testing. Performance was assessed using Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE), and $\mathbf{R}^{\mathbf{2}}$. Results show that the LSTM-Base model (60-day window, 1-day horizon) achieved the best accuracy (MAE $=5.38$, RMSE $=6.73$, MAPE $=3.27 \%, \mathbf{R}^{\mathbf{2}}=\mathbf{0. 8 2}$), while LSTM-LB120-H7 (120-day window, 7-day horizon) performed poorly (MAE $=14.09$, RMSE $=17.44, \mathbf{R}^{2}=-0.34$). These findings highlight that simpler LSTM configurations are more effective for volatile crypto assets, offering both academic insight and practical benchmarks for traders, analysts, and policymakers.