The rapid digitization of commercial, governmental, and legal transactions has created an urgent need for efficient, secure, and transparent dispute resolution mechanisms. Traditional arbitration systems often fall short when handling the complexity and volume of digital evidence, smart contracts, and cross-border interactions. This study proposes a novel AI-powered digital arbitration framework that integrates smart contracts, blockchain-based evidence authentication, and explainable artificial intelligence (AI) to automate and modernize the arbitration process. The framework comprises three core layers: (i) a smart contract-based agreement layer that encodes legal terms and self-executing arbitration clauses; (ii) a blockchain-based evidence management layer that ensures the integrity, authenticity, and traceability of submitted evidence; and (iii) an AI-based arbitration engine that classifies, interprets, and evaluates evidence using transformer and LSTM models, supported by SHAP and LIME for interpretability. A controlled experimental setup was implemented using Ethereum and Hyperledger Fabric testnets, with AI models trained on 1,200 annotated arbitration cases. Results demonstrate a 99.5% reduction in arbitration time, a 92.4% agreement rate between AI and expert rulings, and a 99% accuracy in tampering detection. Furthermore, 87.3% of AI-generated decisions were rated as interpretable and acceptable by legal experts. These findings confirm the system's ability to deliver fast, accurate, and explainable arbitration decisions while complying with legal standards. This research contributes a foundational blueprint for deploying autonomous arbitration systems in digital governance, offering scalable solutions for future applications in smart contracts, e-commerce disputes, and algorithmic legal infrastructure.
To address the limitations of blockchain data storage capacity and uneven dis-tribution, this paper proposes a Chord dual-ring distributed storage method based on virtual nodes. Building upon the original Chord protocol, this approach introduces virtual rings to construct a “storage ring-virtual ring” dual-ring structure. Target virtual nodes are located through routing table lookups, and data is distributed across the storage ring via a name mapping mechanism. Sim-ulation experiments validate the proposed scheme's effectiveness by evalu-ating load balancing and query success rate across varying sharding granulari-ties. Results demonstrate that this approach not only efficiently achieves shard-ed storage for blockchain data but also ensures balanced distribution of block data.
Despite the popularity of Hashed Time-Locked Contracts (HTLCs) because of their use in wide areas of applications such as payment channels, atomic swaps, etc, their use in exchange is still questionable. This is because of its incentive incompatibility and susceptibility to bribery attacks. State-of-the-art solutions such as MAD-HTLC (Oakland'21) and He-HTLC (NDSS'23) address this by leveraging miners' profit-driven behaviour to mitigate such attacks. The former is the mitigation against passive miners; however, the latter works against both active and passive miners. However, they consider only two bribing scenarios where either of the parties involved in the transfer collude with the miner. In this paper, we expose vulnerabilities in state-of-the-art solutions by presenting a miner-collusion bribery attack with implementation and game-theoretic analysis. Additionally, we propose a stronger attack on MAD-HTLC than He-HTLC, allowing the attacker to earn profits equivalent to attacking naive HTLC. Leveraging our insights, we propose \prot, a game-theoretically secure HTLC protocol resistant to all bribery scenarios. \prot\ employs a two-phase approach, preventing unauthorized token confiscation by third parties, such as miners. In Phase 1, parties commit to the transfer; in Phase 2, the transfer is executed without manipulation. We demonstrate \prot's efficiency in transaction cost and latency via implementations on Bitcoin and Ethereum.
Cryptocurrency price prediction poses significant challenges due to the inherent volatility and nonlineardynamics of the market. This study introduces a hybrid stacked modeling framework that integrates machine learning (ML) and deep learning (DL) techniques, capitalizing on their complementary strengths-ML models are effective at capturing nonlinearfeature interactions in structured data, while DL architectures are adept at modeling temporal dependencies in sequential data. The proposed model leverages historical price data, technical indicators, macroeconomic variables, and sentiment metrics, with feature engineering applied to enhance predictive capability. Empirical evaluation was conducted through two experimental setups: (i) short-term, monthly segment analysis and (ii) long-term generalization via five-fold cross-validation. The hybrid model outperformed individual baseline models, achieving up to 18.3% lower RMSE and 6.7% higher directional accuracy. Additionally, it yielded superior risk-adjusted returns, with Sharpe Ratios reaching 0.094 on the Ethereum dataset. Beyond technical improvements, this research offers foresight into digital financial markets, providing a robust tool for investors, institutions, and policymakers navigating the evolving cryptocurrency landscape. The model supports more informed decision-making, enhances market oversight, and contributes to the development of adaptive regulatory frameworks for digital finance.
This research developed a blockchain-enabled framework to enhance secure credentialing and access management for remote healthcare providers and patients across fragmented digital health platforms. Addressing inefficiencies in traditional systems such as lengthy verification delays and data silos, the study employed a design science approach, integrating Hyperledger Fabric and Ethereum smart contracts. Simulations using synthetic healthcare datasets demonstrated a significant improvement, including a 99.99% reduction in credential verification time (to 14 seconds), a 650% throughput increase (to 1,876 TPS), and a 94.7% reduction in security breaches, with 97.8% interoperability success across 234 systems. The framework achieved 99.93% authentication accuracy and 41% administrative cost savings. While results show strong potential, the reliance on simulations may not capture full real-world complexities, and high initial deployment costs remain a constraint. Regulatory compliance, particularly with evolving standards such as HIPAA, was considered essential for implementation. Future work will focus on real-world pilot deployments, AI-driven fraud detection, and the establishment of standardized protocols to support scalability and interoperability. Overall, this study advances secure and efficient healthcare delivery by enabling real-time credentialing and interoperable access, fostering patient-centric care in telemedicine.
Shikah J. Alsunaidi, Hamoud Aljamaan, Mohammad Hammoudeh
Smart Contracts (SCs), self-executing programs on blockchain platforms, are transforming industries such as banking, healthcare, and supply chains through automated, trustless transactions. However, their inherent vulnerabilities have led to severe financial and operational losses, with large-scale exploits causing substantial economic damage. Machine Learning (ML) has emerged as a promising approach for SC vulnerability detection, yet its effectiveness, adaptability, and generalizability remain insufficiently explored. This article comprehensively classifies current Ethereum SC vulnerabilities and attacks. It also surveys 108 ML-based detection methods, covering both traditional models and a structured taxonomy of advanced approaches such as GNN-based, LLM-based, contrastive learning, ensemble, hybrid, meta-learning, and transfer learning techniques. The strengths, limitations, and practical challenges of these methods are systematically analyzed, with particular attention to factors such as detection stages, classification problems, dataset characteristics, feature engineering, performance evaluation, generalizability, detection capability, model aging, and ethical and privacy implications. Additionally, existing datasets on SC vulnerabilities are reviewed and consolidated. By integrating these insights, this work provides actionable guidelines and a foundation for building secure, resilient, and trustworthy SC ecosystems.
This study explores the design and implementation of a blockchain-based system to enhance trust, transparency, and security in academic credentialing. Motivated by the growing distrust in centralized institutions and the inefficiencies of traditional credential verification processes, the research leverages the immutability, decentralization, and transparency of blockchain to develop a tamper-proof mechanism for academic record storage and validation. Using the Ethereum Sepolia test network and real-world student performance data from the Open University Learning Analytics Dataset (OULAD), the system securely issues, verifies, and revokes academic credentials through a custom smart contract developed in Solidity. Each credential is hashed using SHA-256 to ensure student privacy while enabling public, real-time verification. The implementation was conducted in a Google Colab environment using Web3.py and Infura, with batch processing mechanisms and a Web3 interface for seamless interaction. Empirical results reveal performance patterns across modules and highlight opportunities for academic intervention. The system not only demonstrates operational feasibility but also offers a scalable, interoperable, and ethical framework for higher education institutions to combat credential fraud and enhance institutional accountability. Future work will focus on privacy-enhancing cryptographic integrations and decentralized identity standards to further solidify blockchain’s role in education.
The effective management of electronic medical records is critical to deliver high-quality healthcare services. However, existing systems often suffer from issues such as fragmented data, lack of interoperability, and weak privacy protections, which hinder collaboration among healthcare stakeholders. This paper proposes a blockchain-based system to securely manage and share medical records in a decentralized and transparent manner. By leveraging smart contracts and access control policies, the system empowers patients with control over their data, ensures auditability of all interactions, and facilitates secure data sharing among patients, healthcare providers, insurance companies, and regulatory authorities. The proposed architecture is implemented using a private Ethereum blockchain and evaluated through a scenario-based comparison with the Prince Sultan Military Medical City system, as well as quantitative performance measurements of the blockchain prototype. Results demonstrate significant improvements in data security, access transparency, and system interoperability, with patients gaining the ability to track and control access to their records across multiple healthcare providers, while system performance remained practical for healthcare workflows.
Reliable asset price data are critical for the functioning of decentralized finance (DeFi) protocols, particularly those involving collateralized lending. The accuracy of blockchain-based price oracles directly affects key processes such as collateral valuation, liquidation, and risk management. This paper presents a comprehensive empirical analysis of Chainlink Price Feeds (CPFs), the dominant oracle infrastructure in DeFi. We compile a novel dataset of over 150 million observations from 40 CPFs on Ethereum over an 18-month period, matched to benchmark prices from a centralized exchange. To identify the determinants of oracle inaccuracy, we estimate pooled OLS and fixed effects regressions, relating price deviations to design parameters, reporter dynamics, and market conditions. We then introduce a Markov-like state transition framework to model the resolution of target corridor violations, using multinomial logistic regression to estimate transition probabilities. Finally, we exploit position-level data from one of the largest decentralized lending markets and apply entity fixed effects regressions to examine how users adjust collateralization in response to oracle design. Our findings highlight economically significant deviations that are systematically related to oracle accuracy configurations and market stress, and show that users internalize these risks in their financial decisions. The results offer new insights for the design of resilient oracle systems and the management of risk in decentralized financial markets.
Hadis Rezaei, Ahmed Afif Monrat, Karl Andersson, Francesco Palmieri
The deterministic nature of blockchain technology creates fundamental difficulties in producing secure random numbers within smart contracts, a limitation that exposes vulnerabilities in applications such as decentralized finance (DeFi) protocols and blockchain-based gaming platforms. From our observations, the current state-of-the-art detection tools suffer from inadequate precision while dealing with random number vulnerabilities. To address this problem, we propose TaintSentinel, a novel path-sensitive vulnerability detection system designed to analyze smart contracts at the execution path level and gradually analyze taint with domain-specific rules. This paper discusses a solution that incorporates a multifaceted approach, integrating rule-based taint analysis to track data flow, a dual-stream neural network to identify complex vulnerability signatures, and evidence-based parameter initialization to minimize false positives. The two-phase operation of the system involves the construction of semantic graphs and the analysis of taint propagation, followed by pattern recognition using PathGNN and global structural analysis via GlobalGCN. Our experiments on 4,844 contracts demonstrate the superior performance of TaintSentinel relative to existing tools, yielding an F1-score of 0.892, an AUC-ROC of 0.94, and a PRA accuracy of 97%.
The problem of reproducibility of experiments in optimizing validator allocation in blockchain networks with Proof of Stake consensus was investigated, in particular due to the absence of standardized datasets and unified testing methods, which complicates the objective comparison of algorithms. To tackle this issue, we propose a method for building test datasets that rely on deterministic pseudorandom sequence generators and validator profiles calibrated against Ethereum network statistics. Each validator is described by a set of parameters that includes the stake size with the minimum requirement according to Ethereum standards, performance with a uniform distribution, reliability in a high range, network delays depending on the geographical proximity of participants, geographical location according to the actual statistics of validator distribution by regions, quality of network connection, and slashing history according to the violation statistics in the Beacon Chain. Three datasets of different scales were created for small, medium, and large network configurations with fixed initial values of the generators to ensure full reproducibility of experiments. A multi-criteria evaluation system was developed based on a generalized quality indicator that maximizes system throughput and minimizes load imbalance and network delays with scientifically grounded weighting coefficients. The tenfold testing protocol ensures the statistical reliability of results and reduces the impact of randomness on conclusions. The experiments conducted a comparative analysis of four allocation algorithms: a hybrid metaheuristic method based on particle swarm optimization with local search, random allocation with correction, an adapted Ethereum shuffling mechanism, and a greedy algorithm. The experimental results revealed scale-dependent efficiency of the algorithms: the hybrid method provides high optimization quality at all investigated scales, but quadratic growth of execution time limits its application to periodic offline planning of network configuration; the shuffling mechanism demonstrates stable medium-quality results with fast execution; the random method is characterized by moderate speed with variable results; the greedy algorithm shows maximum speed with deterministic results but variable efficiency depending on the network scale. The proposed method forms a basis for standardizing experimental research in Proof of Stake consensus systems. It ensures the objective comparison of new algorithmic solutions for validator allocation in decentralized blockchain networks.
Open access
Advanced Research in Systems and Signal Processing
Yerlan Kistaubayev, Francisco Liébana‐Cabanillas, Aijaz A. Shaikh, Galimkair Mutanov · 6 authors
It has been recognized that Blockchain technology contributes to environmentally sustainable development goals (SDGs). It has emerged as a disruptive innovation capable of transforming various economic and social sectors significantly. This conceptual paper is driven by the need to explore how blockchain, specifically a consortium-based Ethereum architecture, can be integrated into higher education institutions to ensure data sovereignty, integrity, and verifiability while adhering to legal and ethical standards such as GDPR. We propose a multi-layered blockchain-based model for Kazakhstan’s Unified Platform of Higher Education (UPHE). This model employs hybrid on-chain/off-chain data storage, smart contract automation, and a Proof-of-Authority consensus mechanism to address system limitations, including data centralization and inadequate verification of academic credentials. Empirical simulations using Blockscout and Ethereum-compatible tools demonstrate the model’s feasibility and performance. This paper contributes to the growing discussion on educational blockchain applications by presenting a scalable, secure, and transparent architecture that aligns with institutional governance and Environmental, Social, and Governance (ESG) principles. It also supports the objectives of UN SDG 4 (i.e., Quality education) by fostering trust, transparency, and equitable access to verifiable educational credentials.
The increasing prevalence of Maximal Extractable Value (MEV) in blockchain networks has highlighted critical challenges in achieving fair and predictable transaction ordering. On Ethereum, where block builders possess unrestricted control over transaction sequencing, users face significant risks from frontrunning and sandwich attacks, particularly within decentralized finance (DeFi) applications interacting with shared contract states. To address this issue, this paper proposes a hybrid MEV mitigation method employing Lamport-style logical clocks, designed to establish a local causal ordering mechanism within individual smart contracts. The proposed approach equips each smart contract, such as a decentralized exchange liquidity pool, with a local logical timestamp counter. Transactions submitted to the contract carry logical timestamps, enabling the enforcement of a causally consistent execution order. A key benefit of this method is that it does not necessitate alterations to Ethereum’s global consensus mechanism, thus ensuring compatibility with the current Ethereum ecosystem, as well as rollups and modular app-chain architectures. The study details the protocol design, explores various implementation strategies for both on-chain and off-chain execution environments, and addresses resilience against adversarial attempts such as timestamp manipulation and denial-of-service attacks. The primary advantage of this approach lies in its effectiveness in mitigating intra-contract MEV extraction by strictly controlling transaction reordering for conflicting state interactions, while preserving concurrency for non-conflicting transactions. Findings indicate that the use of local Lamport clocks provides a practical, low-overhead solution for MEV-sensitive applications, including decentralized exchanges and rollup sequencing systems.
This paper analyzes the time-varying herding behavior in the non-fungible token (NFTs) and cryptocurrency markets and investigates their interrelationship. Using the daily market data from January 1st, 2020 to April 30th, 2023, our study covers the period characterized by Covid and post-Covid-19 induced global financial market volatility, capturing the dynamics in the global macroeconomic system and the Federal Reserve’s interest rate policy. Based on the rolling window method, our findings show the presence of herding behavior in both markets, where herding behavior in these markets may be influenced by the major events announcements particularly those related to the Federal Reserve's interest rate policy. Vector error correction model (VECM) indicates that the NFT market impacts the price of Ethereum, thereby influencing the broader cryptocurrency market. Such finding contributes to a deeper understanding of the market dynamics. By examining herding behavior, our findings indicate that the NFT market demonstrates relative independence from the volatile prices of the cryptocurrency market, suggesting the potential diversification benefits of incorporating NFTs for investors’ portfolio construction and risk management.
This paper introduces a methodology for software vulnerability detection that combines structural and semantic analysis through software metrics and topic modelling. We evaluate the approach using smart contracts as a case study, focusing on their structural properties and the presence of known security vulnerabilities. We identify the most relevant metrics for vulnerability detection, evaluate multiple machine learning classifiers for both binary and multi-label classification, and improve classification performance by integrating topic modelling techniques. Our analysis shows that metrics such as cyclomatic complexity, nesting depth, and function calls are strongly associated with vulnerability presence. Using these metrics, the Random Forest classifier achieved strong performance in binary classification (AUC: 0.982, accuracy: 0.977, F1-score: 0.808) and multi-label classification (AUC: 0.951, accuracy: 0.729, F1-score: 0.839). The addition of topic modelling using Non-Negative Matrix Factorization further improved results, increasing the F1-score to 0.881. The evaluation is conducted on Ethereum smart contracts written in Solidity.
Nazia Azim, Khair Ul Burria, Muhammad Zain Asghar, Zeeshan Raza · 6 authors
Ethereum blockchain is the market leading platform for decentralized applications and smart contracts that have powered the new age of financial ecosystem. In order to improve security and performance, identify influential nodes, and understand network dynamics on Ethereum it is critical to identify influential nodes in Ethereum. This study explore machine learning techniques for discovery of these nodes using graph based algorithms, centrality measures and clustering methods. It studies the impact of a node in terms of frequency of usage, connectivity and computational power for a node. Finally, this study compare performance of proposed methodology combining supervised learning and graph neural networks to their traditional counterparts and demonstrate approach outperforms existing methods. The study demonstrate that highly influential nodes engage in unique patterns of behavior, which are detectable and categorizable. This study contribute to understanding of the network structure of Ethereum, along with a scalable approach to monitoring and optimising blockchain ecosystems. Moreover the study discuss the implications for network robustness, fraud detection and protocol enhancements, and demonstrate the promise of machine learning for blockchain analytics.
Rodrigo Dutra Garcia, Gowri Ramachandran, Christian Esteve Rothenberg, Daniel Macêdo Batista · 5 authors
The transition to 6G networks is expected to support a broader range of user-centric applications. As these applications expand, Quality of Experience (QoE) has emerged as a key metric for evaluating user satisfaction. However, the use of centralized systems lacks transparency and limits users’ ability to govern their data usage. It also introduces challenges in managing QoE data while preserving privacy. At the same time, verification mechanisms are needed that allow regulators to evaluate compliance without exposing confidential business information. To address this, we propose a decentralized, privacy-preserving QoE system that integrates blockchain with fully homomorphic encryption (FHE). This design enables transparent evaluations between users and service providers by supporting computations directly on encrypted data, ensuring that all information remains protected throughout the process. Users contribute QoE metrics through a decentralized infrastructure and retain control over their data. Regulators can monitor compliance without accessing raw data, and service providers can use encrypted QoE data to perform privacy-preserving computations via smart contracts without relying on a central authority. We developed a proof-of-concept integrating FHE smart contracts compatible with Ethereum Virtual Machine (EVM) blockchains and evaluated their performance using a video streaming dataset. Our results show that encryption and FHE operations consistently occur within milliseconds when tested in a local environment. We also evaluated these operations on a public blockchain testnet. In this setting, our system adds a millisecond-scale delay while supporting privacy-preserving computations directly on encrypted user data.
The Blockchain is an emerging technology that is used in various applications for data security and trustworthiness. In the case of a public Blockchain, the data cannot be edited or deleted. In the case of a consortium and private Blockchain, the data can be edited or deleted based on the assigned permission, and the data privacy can be maintained. Blockchain's smart contract provides security to stored data, but it is vulnerable to various security threats. Smart contracts still suffer from different variabilities like distributed denial of service attacks (DDoS), 51% vulnerability attacks, double-spending problems, and mining Pool attacks. The smart contract, run on a Blockchain framework, is the logical contract between two or more anonymous people without involving a third party. Hyperledger and Ethereum are two important frameworks that support the development of smart contracts using Blockchain technology. This paper has tried to analyze the security issues of smart contracts developed on the Ethereum framework. An application of class scheduling management and student attendance management has been designed to validate and generate a smart contract. Received: 31 May 2025 | Revised: 4 August 2025 | Accepted: 29 August 2025 Conflicts of Interest The author declares that he has no conflicts of interest to this work. Data Availability Statement The data used in this article are virtual data to implement and to establish the algorithm. It is available in GitHub at https://github.com/ashisgitup/e-learning-Blockchain.git. Author Contribution Statement Ashis Kumar Samanta: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Resources, Data curation, Writing — original draft, Writing — review & editing, Visualization, Project administration.
Rashed Alnuman, Tayyab Sajid, Wesam Almobaideen, Qusai Hasan
Abstract Blockchain technology has revolutionized digital financial transactions and asset ownership by enabling decentralized and automated operations through smart contracts. Solidity smart contracts, used in the Ethereum blockchain network, facilitate secure and trustless execution of agreements. However, like any code, smart contracts are prone to vulnerabilities. Considering the assets and value of currency these smart contracts handle, their exploitation leads to severe financial losses and loss of operations. Such exploits have resulted in billions of dollars in stolen or locked assets. In this paper, we present an ensemble multilabel classifier model approach for the automated detection of vulnerabilities in Solidity smart contracts using a real smart contract dataset, with a detailed methodological process that includes processing the dataset. The proposed model stack achieves excellent results with F1 scores ranging from 82.0% to 99.9% for each vulnerability dataset. The proposed model is also compared with common static analyzer tools and models proposed in the literature following a similar approach. Moreover, we package the models into a web application, demonstrating deployment and functionality.
Machine Learning (ML) models are increasingly deployed to detect fraudulent activities in Ethereum, where phishing and scamming attacks pose serious security risks. Despite their promise, these models remain susceptible to adversarial manipulations. In this article, we present a comprehensive evaluation of ML-based Ethereum phishing detectors under a spectrum of adversarial perturbations. Our study examines multiple classifiers, including Random Forest, Decision Tree, K-Nearest Neighbors, Graph Neural Networks, and XGBoost, against rule-based, gradient-based, and black-box adversarial attacks. We conduct detailed feature-level analyses to identify transaction attributes most vulnerable to manipulation, and we evaluate the comparative robustness of classifiers under both targeted and untargeted attack scenarios. To strengthen model resilience, we assess mitigation techniques such as adversarial training and randomized smoothing, demonstrating their effectiveness in improving robustness without significant performance degradation.
The demand for goods transported by Cargo has existed at all predominant times. A large number of shipments are moved daily based on the demand that exists both in the local and the global market. In the current scenario of cargo shipment, the state of freight is usually monitored throughout the shipment process. This is entirely based on the simple temperature-based regulated storage system called cold-chain. Unfortunately, this temperature-based system does not entirely ensure the preservation of cargo shipments. This paper presents the design of a blockchain-powered Decentralized Application (DApp) to monitor Cargo in heavy goods vehicles. It includes implementing the Ropsten test network, which is integrated with a centralized cloud platform. Moreover, details of a complete evaluation of the architecture in terms of its working functionality were added, and its effectiveness in terms of its performance efficiency and real-time operation. To overcome these limitations, alternative solutions, including adopting Layer-2 scaling solutions such as Polygon or transitioning to Proof of Stake (PoS)-based blockchains for faster and more cost-effective transactions, are recommended. Selective use of Blockchain, where only critical violations are recorded, mitigates the issue of high transaction costs. Routine sensor data is efficiently managed using Google Firestore, ensuring optimal cost efficiency. The system currently relies on Infura for blockchain node access, which introduces external dependencies and potential points of failure. To reduce these risks, the adoption of self-hosted Ethereum nodes is recommended for enhanced control and reliability.
Cross-chain interoperability is essential for the next generation of decentralized finance applications, yet existing bridges suffer from security weaknesses, high latency, and fragmented trust models. This paper introduces SnapBridge, a protocol that transfers assets across heterogeneous blockchains using cryptographic state snapshots combined with optimistic verification. A snapshot aggregator collects Merkleized proofs of account states and transaction histories from the source chain. Instead of verifying all proofs on-chain, SnapBridge relies on optimistic execution: transfers proceed immediately but can be challenged within a fraud-proof window. Fraud detection is performed by light clients using succinct verification rules. We implement SnapBridge across Ethereum, Polygon, and Avalanche testnets and benchmark transfer throughput, failure handling, and gas consumption. Results show up to 3× improvement in transfer latency and a 40% reduction in on-chain verification cost compared to multisig-based bridges. The paper evaluates adversarial scenarios such as corrupted aggregators, delayed snapshots, and chain reorgs. SnapBridge provides a modular, safer alternative for cross-chain liquidity flows.
New technologies, such as blockchain, are designed to address various system weaknesses, particularly those related to security. Blockchain can enhance numerous aspects of traditional banking systems by transforming them into digital, immutable, secure, and anonymous ledger. This paper proposes a new banking application ALBank, which is based on blockchain and smart contract technologies. Its functionality relies on invoking functions within smart contracts deployed on the Ethereum blockchain. This approach enables decentralization and enhances both security and trust. In this context, the paper first presents a critical analysis of existing research on blockchain and traditional banking systems, with a focus on their respective challenges. It then examines the Know Your Customer (KYC) process and its various models. Finally, it introduces the design and development of ALBank, a decentralized banking application built on the Ethereum blockchain using smart contracts. The results show that the integration of blockchain and smart contracts effectively addresses key issues in traditional banking systems, including centralization, inefficiency, and security vulnerabilities by storing critical data on a decentralized, immutable ledger, managing processes autonomously, and making transactions transparent to all users.
Neural networks increasingly run on hardware outside the user's control (cloud GPUs, inference marketplaces). Yet ML-as-a-Service reveals little about what actually ran or whether returned outputs faithfully reflect the intended inputs. Users lack recourse against service downgrades (model swaps, quantization, graph rewrites, or discrepancies like altered ad embeddings). Verifying outputs is hard because floating-point(FP) execution on heterogeneous accelerators is inherently nondeterministic. Existing approaches are either impractical for real FP neural networks or reintroduce vendor trust. We present TAO: a Tolerance Aware Optimistic verification protocol that accepts outputs within principled operator-level acceptance regions rather than requiring bitwise equality. TAO combines two error models: (i) sound per-operator IEEE-754 worst-case bounds and (ii) tight empirical percentile profiles calibrated across hardware. Discrepancies trigger a Merkle-anchored, threshold-guided dispute game that recursively partitions the computation graph until one operator remains, where adjudication reduces to a lightweight theoretical-bound check or a small honest-majority vote against empirical thresholds. Unchallenged results finalize after a challenge window, without requiring trusted hardware or deterministic kernels. We implement TAO as a PyTorch-compatible runtime and a contract layer currently deployed on Ethereum Holesky testnet. The runtime instruments graphs, computes per-operator bounds, and runs unmodified vendor kernels in FP32 with negligible overhead (0.3% on Qwen3-8B). Across CNNs, Transformers and diffusion models on A100, H100, RTX6000, RTX4090, empirical thresholds are $10^2-10^3$ times tighter than theoretical bounds, and bound-aware adversarial attacks achieve 0% success. Together, TAO reconciles scalability with verifiability for real-world heterogeneous ML compute.