The paper examines the volatility spillover effects and long-term relationship between cryptocurrencies and traditional financial markets in Türkiye using BEKK-GARCH and DCC-GARCH models. It analyses the perception of crypto assets as a “digital safe haven” in an economy marked by high inflation, exchange rate fragility, and financial uncertainty. Using monthly price data for Bitcoin, Ethereum, BIST-100, and Republic Gold from January 2010 to February 2025, the study applies unit root tests, Johansen cointegration, ARDL bounds, and Engle-Granger tests. Results show no long-term price cointegration, but Bitcoin and Ethereum returns are strongly correlated, with DCC-GARCH results showing a dynamic correlation above 50%, while gold and BIST-100 correlate weakly or negatively. BEKK-GARCH highlights significant volatility transmission from Bitcoin to Ethereum, with BIST-100 maintaining persistent volatility. The study concludes that crypto and traditional markets in Türkiye are not integrated long-term, but short-term interactions exist at the return level, with implications for portfolio diversification and financial stability.
Prof. Suvarna A. Bahir, Tejas Vaidya, Ranjeet Waghmode, , Abhishek Gavand, · 5 authors
Electronic voting systems have gained significant attention due to their ability to improve the efficiency and accessibility of elections. However, traditional voting methods and centralized electronic voting systems face challenges such as vote tampering, lack of transparency, unauthorized access, and delayed result generation. Blockchain technology offers a decentralized and secure solution to address these limitations. This paper presents a Secure Blockchain-Based E-Voting System Using Smart Contracts that leverages Ethereum blockchain technology to provide transparent, secure, and tamper-resistant elections. The proposed system integrates voter authentication, election management, candidate registration, vote recording, and real-time result monitoring within a single platform. Smart contracts developed using Solidity are used to automate election operations and ensure the integrity of voting transactions. The system is implemented using HTML, CSS, JavaScript, FastAPI, MySQL, Ethereum, Ganache, and MetaMask. Votes are securely recorded on the blockchain, preventing unauthorized modifications and improving election transparency. The proposed framework enhances voter trust, reduces dependency on centralized authorities, and simplifies election management. This solution can be effectively used for academic institutions, organizations, and small-scale election environments requiring secure and reliable voting processes. Keywords: Blockchain, Electronic Voting, Ethereum, Smart Contracts, Solidity, Decentralized Voting.
Energy demand in urban and metropolitan regions has been growing rapidly, often exceeding production capacity, leading to imbalances in energy distribution. Existing peer-to-peer (P2P) energy trading models, along with classical algorithms like FCFS and best-fit frameworks in smart cities, address some of these issues. However, they often face challenges such as limited transaction success percentage, inefficiencies in price matching, and privacy concerns during trades. To overcome these limitations, a framework is proposed that integrates game-theoretic pricing-based collaborative trading with Nash equilibrium and an additional pricing mechanism (CoGap) to enhance fairness and transaction success percentage in decentralized energy markets. The proposed framework is implemented on an Ethereum-based blockchain using Solidity smart contracts, incorporating cryptographic security through the Keccak-256 hash function and privacy-preserving zero-knowledge proofs (ZKPs). Moreover, it ensures security and price negotiations while maximizing transaction efficiency. Simulation results demonstrate that CoGap consistently achieves higher transaction success rates compared to four state-of-the-art collaborative energy trading schemes.
Transaction monitoring and efficient audit management have become increasingly importantin modern financial systems. Traditional centralized databases and auditing methods often face challengesrelated to security vulnerabilities, fraudulent activities, and data manipulation. A blockchain-based financialtransaction monitoring system integrates smart contracts, decentralized ledgers, and audit trails to automatefinancial operations, enhance transparency, and reduce fraud risks. The proposed architecture is implementedon Ethereum and Hyperledger Fabric platforms, enabling automated transaction validation and executionthrough smart contracts. All transactions are stored in an immutable decentralized ledger, while audit trailsare generated and maintained automatically. Simulation results demonstrate a 40–60% reduction in fraudulentactivities and up to a 70% decrease in audit processing time compared with conventional approaches. Theapplication of cryptographic algorithms and Zero-Knowledge Proofs further strengthens data security andprivacy protection. The proposed solution contributes to the improvement of financial control and auditingsystems within the framework of the digital economy.
Execution Tickets (ET) have emerged as a leading proposal for mitigating MEV-related centralization risks by internalizing MEV through a protocol-level lottery system. This paper provides an empirical game-theoretic analysis (EGTA) of the ET mechanism under an infinite-supply design, modeled as a Tullock contest. We evaluate a 2-slot lookahead window as a minimal temporal design that limits multi-slot MEV while preserving support for user pre-confirmations. By introducing a forfeiture parameter, we parameterize a continuum between All-Pay and Winner-Pay regimes. We then map the fairness-revenue frontier, revealing a fundamental design tension: higher contest decisiveness and forfeiture rates can improve protocol revenue, but may reduce allocation fairness by entrenching dominant builders. We identify a quantitative Goldilocks zone that balances MEV-capture efficiency with market diversity.
Ethereum is a widely adopted blockchain platform that supports a large number of decentralized applications. Despite its rapid growth, Ethereum remains vulnerable to security threats, particularly phishing attacks that exploit transactional behavior. This study investigates the effectiveness of tree-based ensemble learning models for detecting phishing transactions on the Ethereum network using an imbalanced transaction dataset. Seven tree-based ensemble classifiers are empirically evaluated under a cost-sensitive learning framework, with performance assessed using the Matthews Correlation Coefficient (MCC) as the primary metric. The results show that boosting-based ensembles substantially outperform bagging-based approaches and a single decision tree. In particular, Gradient Boosting achieves the strongest detection performance with an MCC of 0.9742, while CatBoost provides a trade-off between detection performance and computational efficiency, achieving competitive detection accuracy with the lowest average inference time (approximately 1.54 µs per transaction). The findings demonstrate that accurate and robust phishing detection can be achieved using a compact feature representation, enabling practical deployment with reduced computational overhead.
Cryptocurrency fraud on blockchain platforms continues to cause substantial financial losses, creating an urgent need for detection systems that are not only accurate but also interpretable for operational and regulatory use. In this paper, we propose an explainable framework for Ethereum fraud detection integrating an XGBoost ensemble with TreeSHAP. This system achieves high predictive performance (96.3% F1-score, 96.6% recall) while providing model-level transparency via an interactive chatbot interface. Evaluation using fidelity and stability metrics confirms the reliability of the SHAP-based insights, while user-role simulations demonstrate that our structured delivery enhances clarity and actionability over standard visualizations. This work offers a practical, transparent foundation for deploying robust AI in high-risk financial environments without sacrificing accuracy.
NFT (Non-Fungible Token), son yıllarda kripto varlık ekosisteminde önemli bir dönüşüm yaratmış dijital varlıklardır. Dijital sanat eserlerinden koleksiyonluk eşyalara, oyun içi varlıklardan sanal gayrimenkullere kadar birçok alanda kullanılmakta olup, dijital içeriklerin özgünlük ve sahiplik niteliklerini kripto varlık biçiminde temsil etmektedir. Bu çalışmada NFT kavramı, tarihsel gelişimi, kullanım alanları ve türleriyle, NFT’lerin güvenilirliğini sağlayan Blokzincir, ikinci nesli Ethereum ile akıllı sözleşmeler gibi teknik yapısı üzerinde durularak hukuki niteliği konusunda değerlendirmeler yer almaktadır.
Joel Poncha Lemayian, Ghyslain Gagnon, Kaiwen Zhang, Pascal Giard
Cryptographic wallets play a vital role in securing digital assets within blockchain networks by managing private keys that authorize secure transactions. However, side channel analysis (SCA) attacks have become a serious threat, enabling attackers to extract sensitive information by exploiting algorithmic weaknesses in microcontroller-based wallets, resulting in the loss of millions of dollars in digital assets. In hierarchically deterministic (HD) systems, the compromise of a single primary key can endanger all subsequent child keys, while the use of independent keys for each account introduces complexity and challenges in key management. This work presents HardVault, a field programmable gate array (FPGA)-based cryptocurrency wallet that supports both Bitcoin and Ethereum. HardVault introduces the first hardware wallet architecture that implements both non-deterministic (ND) and HD key generation modes directly in hardware, giving users the flexibility to choose either approach based on their security and usability needs. By leveraging constant-time operations and hardware-enforced private-key isolation, the design significantly improves resilience to SCA attacks. In addition, the architecture prioritizes resource efficiency to minimize area usage without compromising security, making it well-suited for compact, portable hardware wallet applications. Implementation on a ZCU104 FPGA shows that HardVault uses only 27% of available look-up tables (LUTs). Compared to the Trezor One cryptocurrency (crypto) wallet, the proposed implementation achieves$9\times $higher energy efficiency,$8\times $lower latency, and$7\times $higher throughput.
Open access
Blockchain Technology Applications and Security
Physical Unclonable Functions (PUFs) and Hardware Security
This report synthesises findings from 3 peer-reviewed papers addressing the following research question: How does the integration of persistent homology-based topological features in MTGCL compare to other graph contrastive learning methods (e.g., GTCL, GCMC) in terms of anomaly detection accuracy and. Recently, artificial intelligence (AI) and blockchain have become two of the most trending and disruptive technologies. Blockchain technology has the ability to automate payment in cryptocurrency and to provide access to a shared ledger of data, transactions, and logs in a. 6 claims were extracted from source literature; 6 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.7/10. This report is a machine-generated literature synthesis and does not constitute original research. Research goal: How does the integration of persistent homology-based topological features in MTGCL compare to other graph contrastive learning methods (e.g., GTCL, GCMC) in terms of anomaly detection accuracy and inference latency on large-scale Ethereum transaction datasets? Autonomous literature synthesis. Automated review score: 8.7/10. Full text and citation available at Assignee Research.
Real-world asset tokenization is often presented as a mechanism for improving the liquidity of traditionally illiquid assets. However, on-chain representation and secondary-market liquidity are distinct outcomes. This paper examines whether tokenized real-world assets exhibit meaningful observed liquidity and identifies the token characteristics associated with higher market activity. Using token-level data from RWA.xyz and supplemental contract-level observations from Etherscan, the study constructs an Ethereum-based monthly panel of non-stablecoin real-world assets across three prominent categories: U.S. Treasury-backed tokens, gold-backed commodity tokens, and private-credit-related tokens. Liquidity is measured using turnover, active addresses, and an active-month indicator. The empirical design combines descriptive statistics, non-parametric group tests, and exploratory panel regressions suited to short and sparse token histories. The results show substantial heterogeneity across asset categories. Gold-backed tokens exhibit broader holder bases and more persistent on-chain activity than many Treasury and private-credit-related products, while outstanding asset value alone does not reliably predict observed liquidity. The paper contributes to the literature by developing a clearer empirical measurement framework for real-world-asset liquidity and showing that tokenization and liquidity should be analyzed as distinct outcomes.
We describe a verification pipeline that takes production Rust cryptographic code and produces machine-checked correctness proofs in Lean 4. The pipeline combines three components: symbolic extraction tools (Charon and Aeneas, or Hax) that lift Rust into Lean 4; formal cryptographic specification libraries (ArkLib and CompPoly, from the Verified zkEVM project) that provide the mathematical targets; and AI provers (Aristotle from Harmonic AI and Aleph from Logical Intelligence) that close the resulting proof obligations. Every proof is checked by the Lean kernel, so AI output cannot compromise soundness. Within the scope of the Ethereum Foundation's zkEVM Verification Project, we applied the pipeline to cryptographic primitives in Plonky3 (FRI folding, Mersenne31 and KoalaBear field arithmetic, Horner polynomial evaluation) and RISC Zero (Merkle inclusion verification). In addition, Aleph authored proofs of two bounds-style theorems in Plonky3's compute_log_arity_for_round that previously stood as sorry. The paper describes the architecture, walks through a running example based on Aleph's two proofs, reports which classes of proof obligations AI closed and which required manual work, and discusses the engineering gaps we encountered: Lean 4 toolchain drift across tools and specific Aeneas/Hax extraction limits. We also document concrete missing lemmas, tactic gaps, and code-generation friction points discovered during proof development. We hope this contribution lowers the barrier to adoption of formal verification and facilitates more effective use of AI in this pipeline. The result is a working pipeline for formal verification of Rust, with kernel-checked proofs and reproducible artefacts.
The proliferation of AI-generated synthetic media poses a critical threat to the integrity of digital evidence in legal and forensic contexts. Existing deepfake detection systems typically address a single modality and provide no mechanism for tamper-proof evidence preservation. We present DeepFake Forensics AI, a unified platform that detects synthetic media across image, video, and audio modalities, identifies generative architecture fingerprints, and anchors forensic evidence immutably on the Ethereum blockchain. Our system trains four independent neural networks from scratch: an EfficientNet-B4 image detector (AUC = 0.9868), a Bidirectional LSTM video detector (AUC= 0.9628), an ECAPA-TDNN audio detector (EER = 18.63%), and a novel GAN fingerprinting module (accuracy = 99.88%) that identifies the generative architecture behind a fake image. Evidence files are hashed with SHA-256, stored on IPFS via Pinata, and registered on-chain via a Solidity smart contract with role-based access control. The platform provides a React frontend and FastAPI backend suitable for deployment in forensic and legal workflows. To our knowledge, this is the first system to unify multi-modal deepfake detection with blockchain-based chain-of custody management.
Abstract As AI agents evolve into autonomous economic actors, verifiable and legally binding identity frameworks become critical. This paper presents Ricardian-TEA , a novel architecture combining Triple-Entry Accounting (TEA), Ricardian Contracts, and Distributed Ledger Technology to assign “Legal-Technical Identities” to AI agents. We provide rigorous mathematical foundations: a Ricardian-TEA Integrity Theorem proving that constraint enforcement, non-disputability, and identity binding hold with overwhelming probability under standard cryptographic assumptions, and a Cyber-Chama Convergence Proposition characterising reputation-based trust dynamics. The framework ensures GDPR compliance via Zero-Knowledge Architecture and Crypto-Shredding. Proof-of-concept implementations on Ethereum Sepolia and Bitcoin SV testnets demonstrate chain-agnostic applicability, achieving at worst 1.4 s latency per transaction while maintaining 100% auditability of AI transactions.
Connects to 16 breakthroughs. AUM Inflow Despite Price Slide - TipRanks From GoogleNews (271,272,274,275,276,277,278,279,285,286,287,288,290,291,293,294). Avg score: 0.24 Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com
Muhammad Umar Janjua, Akshaya Mani, Uğur Şen, Daniel Kaiser
Privacy and anonymity of validators, especially regarding IP address linkability, are essential to protect the Ethereum network from various attacks. Network-level attacks, such as DoS, can interrupt validators and affect the overall security of the Ethereum network. Correlating the IP addresses of validators with their identities, along with knowledge about their action slots can be exploited by attackers to cause network delays, MEV exploitation, and finality risks. Therefore, ensuring the unlinkability of a validator's IP and identity is crucial for maintaining the network's trust and resilience. In this techreport, we first provide a review of the existing network and consensus layer techniques that have been proposed for maintaining validator privacy in the Ethereum blockchain. Secondly, we evaluate a Tor-based protocol named Tor push that helps unlink validator identities (IDs) from their nodes' IP addresses, thereby making it difficult to determine any end-to-end correlation between validator IDs and IP addresses of validators' beacon nodes. To evaluate the effectiveness of Tor push, we present a working, deployed proof-of-concept (PoC) implementation in the Nimbus Ethereum client. Our PoC deployment pushes attestations, aggregations, and block proposals over Tor to the Goerli testnet. Furthermore, we also analyse the security and latency of Tor push. Our experimental results suggest that Tor can be incorporated into the existing Ethereum network with a tolerable latency overhead of 613.82 ms on average and without compromising the overall network performance while enhancing the location privacy of validators in the Ethereum network.
Onur Eren Arpaci, Florian Kerschbaum, Sujaya Maiyya
Encrypted cloud storage can hide data contents but still leak sensitive information through access patterns. ORAM addresses this by hiding access patterns, but existing ORAM systems are too inefficient to deploy in practice. We present Cloak, an oblivious storage system that dramatically improves performance by leveraging a simple, widely observed property of real workloads: temporal locality, where recently accessed items are more likely to be accessed again soon. Instead of trying to make server accesses look perfectly uniform, Cloak makes server traffic follow a fixed, "recentness-biased" pattern and then uses real queries to fill as much of that traffic as possible. When the workload exhibits temporal locality, Cloak achieves overheads as low as $1.1\times$ over a non-oblivious and unencrypted baseline. Importantly, this heuristic affects only performance, not security. We evaluate Cloak on Netflix click-stream and Ethereum transaction traces, achieving 165,000 and 157,000 operations per second, respectively, on a single machine.
This study investigates the dynamic relationship between network activity and transaction fees in the Ethereum blockchain by analysing the interaction between Gas Used and Gas Price through a multivariate time series model. The objective is to determine whether variations in network demand influence short-term gas price fluctuations. Daily data of Gas Used and Gas Price were transformed into different logarithmic forms to ensure stationarity. The Augmented Dickey–Fuller test confirmed that both variables are stationary at the five percent significance level, with ADF statistics of −6.21 for Δlog (Gas Used) and −7.12 for Δlog (Gas Price), and p-values below 0.001. The Vector Autoregression model was estimated with an optimal lag length of fourteen days, selected using the Akaike Information Criterion, reflecting the persistence of network and fee dynamics. The results of the Granger causality test indicate a unidirectional causal relationship from Gas Used to Gas Price, with an F-statistic of 3.72 and a p-value of 0.018, suggesting that fluctuations in network demand significantly precede changes in gas pricing. The reverse direction is not significant, with an F-statistic of 1.26 and a p-value of 0.28, indicating that transaction fees do not predict network activity. The impulse response analysis shows that a one standard deviation shock in Gas Used increases Gas Price for two to three days before returning to equilibrium, while shocks in Gas Price have minimal effects on Gas Used. These findings confirm that Ethereum’s fee market operates primarily as a demand-driven mechanism were congestion and transaction volume shape short-term gas price movements.
Zishan Ashraf Mohammad, Nick Harkiolakis, Saman Sarbazvatan
Although there has been a massive increase in the size and complexity of the cryptocurrency ecosystem, most of the academic research into the relationship between token design parameters and the long-term value of a given token is still very much in its infancy. Most of the research in tokenomics is theoretical in nature, based upon frameworks for understanding, or is focused solely on observing a specific time frame. The authors of this paper address the above mentioned void by studying the statistically significant relationships between five on-chain tokenomic variables--transaction gas fees, total value locked (TVL), token unlocks, tokens burned, and governance concentration (as measured using the Gini coefficient) -- and the market price of Ether (ETH) during a 52 months observation window that began in August 2021 and ended in September 2025. The data for the study consisted of bi-weekly observations (n = 108) which allowed researchers to use three different analytical methods--Spearman correlation analysis, log-linear multiple regression analysis, and an error correction model (ECM) after conducting Johansen cointegration and unit root tests. A cointegrating equation among the variables was established through Johansen Trace Testing, indicating that all of these variables do indeed exhibit a long-run equilibrium relationship. The ECM revealed that the total amount of funds “locked” into smart contracts (“total value locked”) was the strongest single predictor of the price of Ether in both the long run (beta = 0.8, p < 0.001) and short run (beta = 1.18, p < 0.001) specifications. Additionally, it was found that token unlocks have a negative relationship with price (beta = −0.22, p < 0.001). Gas Fees (beta = 0.2, p = 0.021) and tokens burned (beta = 0.15, p = 0.039) had positive coefficients at the 0.01 level in the long-run specification; however, both exhibited extremely high levels of multicolinearity (Variance Inflation Factor>28,000), likely due to their technical/operational linkages under EIP-1559. Voting power did not demonstrate a statistically significant relationship to price (rho =0.143, p > 0.05).
India's asset management systems, especially land records, property registries and ownership documents, face major challenges such as fraud, ownership disputes, slow manual verification and fragmented documentation. These issues affect citizens, government departments, financial institutions and real-estate stakeholders. Blockchain technology provides an opportunity to improve asset management by creating tamper-resistant records, transparent transaction history and automated workflows through smart contracts. This paper studies the use of blockchain platforms for asset management in India with a comparative focus on Hyperledger Fabric and Ethereum. The study analyzes technical architecture, performance, privacy, cost, scalability and implementation barriers. It also considers Indian use cases such as Telangana land parcel initiatives, Karnataka Bhoomi-related digital land record modernization and national-level blockchain adoption efforts. The findings show that Hyperledger Fabric is more suitable for regulated government asset systems because it provides permissioned access, privacy channels, higher transaction throughput and lower operational cost. Ethereum is useful for public transparency and open applications, but its public-chain gas cost, lower throughput and regulatory challenges reduce suitability for high-volume government asset records. The paper concludes that a permissioned blockchain model with proper standards, legacy-system integration, legal recognition and rural digital infrastructure can support scalable blockchain-based asset management in India.
A decentralized ecosystem can capture value and still fail to fund the actors who keep it running. Users may pay fees, tokens may appreciate, issuers may earn revenue, and protocols may burn value, but none of these facts by itself shows that authors, miners, validators, suppliers, storage providers, or other critical participants are actually compensated. This paper argues that traditional value-capture analysis often assumes a centralized pool: once value is captured, it can be reallocated through budgets, contracts, payroll, or managerial discretion. Decentralized ecosystems do not have this default pool. They require routed closure: captured value must pass through a verifiable route to a specified critical incentive recipient, and it must be sufficient relative to that recipient's reward requirement. We formalize this distinction through Route-Admissible Value and operationalize it with the External Value Routing Closure protocol. A contrast set including YouTube, Steem/Steemit, Bitcoin, Ethereum, Aave, Filecoin, USDC, and XRP shows why revenue, fees, burns, token prices, or market capitalization should not be mistaken for sustainable incentive funding.
Pedro Henrique F. S. Oliveira, Heder S. Bernardino, Saulo Moraes Villela, Edelberto Franco Silva · 6 authors
O Ethereum é uma plataforma de criptomoedas que permite a execução de contratos inteligentes, programas autônomos que operam em uma rede descentralizada. As vulnerabilidades nesses contratos representam grandes riscos financeiros e de segurança nos ecossistemas blockchain, motivando a automatização do processo de detectá-las. Este trabalho estuda a detecção de vulnerabilidades em contratos inteligentes Ethereum usando embeddings derivados de bytecode. Embeddings são representações vetoriais geradas por modelos de linguagem, que capturam as características estruturais de texto. Essas representações foram usadas como entrada para os algoritmos de regressão logística, árvore de decisão e floresta aleatória, com o fim de detectar quais contratos possuem vulnerabilidades. Os resultados mostram que os embeddings contêm informações úteis para distinguir contratos vulneráveis de não vulneráveis. O estudo também constata que a alteração da distribuição original dos dados durante o treinamento afeta significativamente o desempenho, destacando a sensibilidade das abordagens baseadas em embeddings às estratégias de amostragem.
Vladimir Kovšca, Zrinka Lacković Vincek, Suzana Keglević Kozjak
Prior research on cryptoasset valuation has largely adapted discounted cash flow (DCF) models by treating staking rewards and transaction fees as productive cash flows, while insufficiently accounting for monetary characteristics and strategic flexibility inherent to decentralized platforms. This study investigates whether such cashflow based approaches systematically undervalue Ethereum. The central hypothesis is that Ethereum’s intrinsic value cannot be adequately explained by DCF valuation alone, and that monetary premium and technological optionality constitute economically significant components of value. To examine this hypothesis, a multi-layer valuation framework is applied using network and market data from 2022–2025, combining a DCF model, a monetary premium benchmarked against gold based on relative scarcity and adoption, and a real option uplift reflecting future expansion potential. Monte Carlo simulation is employed to test the robustness of the results. The findings indicate that while DCF-based valuations remain relatively stable, total intrinsic value is highly sensitive to assumptions regarding monetary adoption and strategic optionality. These results underline the importance of layered valuation frameworks for decentralized platforms.
This study investigates the predictive performance of decomposition-based deep learning models through a focused case study on Ethereum price forecasting. Using hourly Ethereum price data from 5 September 2020 to 13 July 2025, we develop hybrid forecasting frameworks that integrate three signal decomposition techniques—Wavelet Decomposition (WD), Variational Mode Decomposition (VMD), and Empirical Mode Decomposition (EMD)—with a Long Short-Term Memory network enhanced by an attention mechanism (LSTM–Attention). The decomposition methods are first applied to extract multiple frequency components from the original time series, allowing the forecasting model to capture both short-term fluctuations and long-term dynamics inherent in this specific digital asset. Each decomposed component is then modeled using the LSTM–Attention architecture, and the forecasts are aggregated to produce the final prediction. The predictive performance of the proposed models is evaluated using MAE, MSE, RMSE, and MAPE, and the results are compared with benchmark models including ARIMA-GARCH and standard LSTM–Attention. Forecast accuracy is assessed through out-of-sample one-step-ahead predictions, and robustness is ensured by averaging results across 10 independent runs. The empirical results demonstrate that incorporating decomposition techniques substantially improves forecasting accuracy. Among the tested models, the EMD–LSTM–Attention framework achieves the best performance, producing the lowest forecasting errors. While focused on the Ethereum market, these findings highlight the effectiveness of combining signal decomposition and attention-based deep learning architectures to enhance predictive performance in high-volatility cryptocurrency environments.