We present Y.I.N.-LLM, a privacy-preserving training architecture for Large Language Models that mathematically guarantees non-memorization of training data. The core innovation is the mandatory DPâZKâHE ordering (Differential Privacy â Zero-Knowledge Proof â Homomorphic Encryption) applied to transformer gradients during training. Key results: (1) 2.3% accuracy loss at Δ=1.0 privacy versus 15-40% with standard DP-SGD; (2) zero extractable training data across all tested attack vectors; (3) native GDPR Article 17 "right to be forgotten" compliance via cryptographic gradient subtraction; (4) EU AI Act Article 50 transparency compliance through verifiable privacy proofs. The Non-Memorization Theorem establishes that for any model M trained with Y.I.N.-LLM parameters (Δ, ÎŽ), the probability of verbatim reproduction is bounded: P[M outputs y | x â training] †e^Δ · P[M outputs y | x â training]. This transforms copyright defense from argument to mathematics. Y.I.N.-LLM addresses the $10B+ memorization litigation crisis (NYT v. OpenAI, Getty v. Stability AI, Authors Guild v. OpenAI) by providing the first mathematically verifiable non-memorization guarantee with practical accuracy preservation. Patent Protected: U.S. Provisional Application 63/946,118 (filed December 21, 2025).
Digital registries are essential for global commerce, intellectual property protection, and cultural preservation. However, they face challenges like centralization risks and evolving security threats. This chapter proposes a framework that utilizes Non-Fungible Token (NFT) technology to develop secure and transparent digital registry systems. Our decentralized architecture eliminates single points of failure while ensuring high performance. We incorporate smart contracts for automated operations, multi-chain compatibility for scalability, and zero-knowledge proofs for privacy. Experimental validation shows a system performance of 33.22 transactions per second with 26-millisecond latency, outperforming many existing solutions while maintaining cost-effectiveness at 126,276 gas units per registration. Comparative analysis with centralized systems (ISBN, DOI, and ISSN) and blockchain alternatives (ENS and IPFS) highlights significant advantages in security and interoperability. Additionally, our economic analysis suggests potential cost reductions of 60â80% compared to traditional registries, enhancing service quality and accessibility. This research contributes to the practical implementation of blockchain-based registry systems, helping organizations consider NFT adoption while addressing scalability and security needs.
Ahmad Musamih, Ibrar Yaqoob, Khaled Salah, Raja Jayaraman · 5 authors
Large Language Models (LLMs) are increasingly embedded in intelligent systems across domains such as healthcare, finance, and smart infrastructure. However, their reliance on centralized data pipelines raises unresolved challenges concerning provenance, accountability, and verifiable trust. As the demand for transparent and regulation-aligned AI grows, these challenges have become central to the responsible deployment of intelligent systems. This review examines how blockchain technology can address them by introducing decentralized integrity, immutable audit trails, and cryptographic verification into the LLM lifecycle. Through a structured synthesis of current research, we identify conceptual and architectural gaps that limit trustworthy data management, inference authentication, and explainability. To bridge these gaps, a methodological framework is proposed that integrates blockchain mechanisms across the LLM pipeline using smart contracts, Merkle-based commitments, and decentralized storage. The frameworkâs feasibility is demonstrated through an illustrative prototype, confirming its practical applicability for building verifiable and transparent AI infrastructures. We further outline application domains such as healthcare, smart cities, Industry 4.0, and supply-chain management, where blockchain-anchored LLMs can enhance auditability and regulatory compliance. The review concludes by highlighting key insights and challenges for future research, emphasizing the need for decentralized attestation models, scalable verification protocols, and governance mechanisms that advance accountable and privacy-preserving intelligent systems.
Open access
Artificial Intelligence in Healthcare and Education
The rapid adoption of blockchain technology has intensified the need for robust smart contract security mechanisms. However, traditional rule-based or static analysis tools often fail to detect context-dependent vulnerabilities embedded in complex contract logic. This study proposes a deep learning framework for automated smart contract vulnerability classification using a Bidirectional Long Short-Term Memory (BiLSTM) network integrated with an Attention Mechanism. The model was trained and evaluated on the SC_Vuln_8label.csv dataset, comprising 12,520 labelled Solidity smart contracts categorized into eight distinct vulnerability types, including Re-entrancy, Integer Overflow, and Short Address Attack. Through bidirectional contextual learning and attention-based feature weighting, the proposed model achieved 93.7% test accuracy, 0.93 precision, and a macro F1-score of 0.92, outperforming baseline models such as CNN, GRU, and standard LSTM by up to 5.3 percentage points. Attention heatmap analysis further revealed the modelâs interpretability by highlighting vulnerability-prone code segments (e.g., call.value, send(), and withdraw() functions) consistent with expert-identified risk indicators. These results demonstrate that the BiLSTM + Attention framework not only enhances vulnerability detection accuracy but also provides transparent and explainable reasoning, offering a reliable foundation for AI-assisted smart contract auditing systems in blockchain security.
The explosive gains of FinTech-enabled digital payments have raised concerns about transaction privacy, the leaking of identity information and regulatory compliance on public blockchains. Existing privacy-preserving payment solutions either have a high computational overhead or do not offer controlled auditability as demanded by financial regulators. This research addresses the problem of ensuring good privacy of transactions while guaranteeing lawful transparency of decentralized payment systems. The goal is to create a blockchain payment framework that incorporates zero-knowledge proof (ZKP) which will ensure payer anonymity, transaction unlinkability and selective regulatory disclosure. The proposed method combines cryptographic identity commitments, private transaction circuits with zk-SNARK and gas optimized smart contract verification with controlled audit proofs. The framework is tested on the Private-FinPay data set that contains two million transactions. Experimental results indicate that the proposed ZKP-FinPay can achieve$\mathbf{1, 2 0 0}$transactions per second, verification latency of$\mathbf{1 2 0}$ms, anonymity set of 50,000 users, and 0.5% probability of privacy leakage, which is better than the five state-of-the-art privacypreserving payment protocols. These findings confirm the viability of regulatory-compliant privacy preservation of FinTech blockchain systems as being technically feasible and practically scalable.
G. Sreenivasulu, Bathula Siva Nageswara Rao, C. Rama Krishna, Srikanth Lukka · 6 authors
This study presents a comprehensive comparative research of the significant blockchain consensus algorithms, such as Proof of Work, Proof of Stake, Delegated Proof of Stake, Practical Byzantine Fault Tolerance, Proof of Authority, and hybrid mechanisms, and the purpose of it is to assess the performance, safety and applicability of blockchain to the modern use of blockchain. The studies analyze the key metrics, including throughput, latency, resource consumption, finality behavior, and fault tolerance in various network conditions based on a quantitative, simulation-based methodology with the help of secondary datasets. The results indicate that there are high levels of performance differences among consensus algorithms, as permissioned and delegated algorithms show better efficiency, and low latency, whereas public mechanisms put more emphasis on decentralization, disregarding speed and energy efficiency. The paper identifies the trade-offs inherent to consensus design and points out that no one mechanism is optimal, instead it needs to be chosen based on applicationspecific factors to do with scalability, trust, security, and decentralization. These insights help gain better insight into the issue of consensus behavior and make future choices regarding building the blockchain system.
P. Chinnasamy, N. Hemanth Reddy, K. Manjusri, P. Kusuma Priya · 5 authors
Medi Chain is a system that is established to introduce a higher degree of trust and transparency into the process of medicine supply. In the current times, counterfeit and bootleg drugs are a point of serious concern, particularly in cases where the physician prescribes them. Medicine batches are tracked and recorded by Medi Chain via blockchain since the stage of manufacture to the point of sale. The data stored is unchangeable and unbreachable as all the data is stored on the Sepolia Ethereum network in the form of smart contracts. Through QR- based checks, the platform enables users of the site to scan a code and instantly access essential information, including the source of the medication, who touched it, and the presence of a valid prescription pivotal to that prescription. This has made the system easy to use as the blockchain logic is written in Solidity and Web3.js, and the user interface is written in React.js and Tailwind CSS. Firebase is used to deal with secure log in, document uploading, and storage of prescription files. The system includes some basic yet significant precautions to ensure that the process of medicine handling happens safely in all stages. Each medicine flow remains exposed and safe and cannot be abused or misused. MetaMask logins, quick scans on QR, allow its users to quickly verify authenticity, making sure that prescriptions are adhered to.
The convergence of the Internet of Things and edge computing represents a fundamental transformation in distributed computing architecture. Traditional cloud-centric models introduce latency and connectivity dependencies flawed for time-touchy packages. Side computing addresses such constraints by positioning computational sources at network peripheries. Distributed processing paradigms restructure data pipelines through intermediate layers between endpoint devices and centralized infrastructure. Fog nodes extend cloud capabilities to locations where data originates. Tiered computation models distinguish between device-level processing, gateway computation, and cloud-based analytics. Aspect synthetic intelligence allows deployment of state-of-the-art machine learning models on resource-limited hardware. Neural network compression strategies consisting of quantization and pruning lessen version complexity while keeping accuracy. Fifth-generation wireless networks provide a connectivity fabric essential for distributed deployments. Multi-access edge computing positions processing resources at radio access network edges. Computation offloading transfers tasks from mobile devices to edge servers strategically. Security frameworks address expanded attack surfaces through zero-trust models and blockchain-based identity management. Distributed ledger architectures eliminate centralized credential repositories. Smart contracts automate security policy enforcement across edge networks reliably.
We investigate whether China's 2021 mining ban transformed Bitcoin from a speculative vehicle into a macro-sensitive asset. Using daily data from 2017-2025, we document a decisive structural break. Pre-2021, volatility was endogenous, driven by raw trading volume rather than fundamentals. Post-ban, however, internal microstructure noise loses predictive power. Instead, volatility is now driven by macroeconomic anxiety: Wikipedia searches for "Inflation" improve forecast accuracy by over 7%. We further uncover a "dual narrative" where inflation attention predicts crash risk, while "Recession" queries (pivot speculation) drive rallies. These findings suggest the regulatory shock successfully curtailed noise trading, allowing macro-fundamentals to dominate price discovery.
With the widespread use of smart contracts in blockchain applications, particularly in the consumer Internet of Things (CIoT), the security of smart contracts has become increasingly critical. CIoT refers to an IoT environment where various consumer devices are intelligently connected and interact via the internet. In this context, smart contracts are frequently used to automate tasks such as device control, data sharing, and transaction verification. However, vulnerabilities in smart contracts can lead to system attacks, thereby compromising the security of the entire IoT network. The Cascade Graph Convolutional Network-based Vulnerability Detection Framework for smart contracts (CGCN-DF) proposed in this study effectively enhances the security assessment of smart contracts in CIoT applications. Devices and systems in CIoT environments typically exhibit high heterogeneity and complex interaction patterns, but a single graph structure cannot fully capture the multidimensional behavioral features and complex structural relationships of smart contracts. To address this issue, this paper introduces the Semantic Contract Graph (SCG), which integrates three graph representationsâAbstract Syntax Tree (AST), Control Flow Graph (CFG), and Data Flow Graph (DFG)âinto a unified graph structure, comprehensively covering different aspects of the code. Furthermore, as smart contracts in CIoT environments often involve real-time data flows and complex execution paths, the CGCN-DF framework employs a cascading mechanism that performs three-level graph convolutional processing through relational, Meta-path structures, and cyclic structures. This approach extracts rich and complementary information from multi-level features, explicitly models the dynamic interactions among syntax, execution paths, and data flows, and enhances the modelâs contextual awareness of vulnerability-triggering conditions. Ultimately, the framework achieves coarse-grained detection at the contract level and fine-grained detection at the line level. Experimental results demonstrate that the proposed method can effectively localize vulnerabilities down to specific code lines. This not only enhances the precision and practicality of smart contract vulnerability detection but, more importantly, contributes an innovative technical framework and theoretical methodology to the CIoT fieldâparticularly in areas such as DSL program analysis and the intersection of IoT and blockchain security. This work thereby helps advance the field toward more refined and context-aware security analysis aligned with the realistic characteristics of complex systems.
The digital payments landscape is undergoing a fundamental transformation fueled by innovative technologies like blockchain. While often associated with cryptocurrencies, blockchain's potential extends far beyond mere transactional efficiency. This distributed ledger technology offers a unique blend of security, transparency, and immutability, making it a compelling avenue for reshaping the very nature of digital payments. Purpose: The research paper will offer insights into the theoretical foundations, practical use cases, and potential challenges of integrating blockchain technology with existing systems in India. Objective: This research paper aims to deliver a comprehensive conceptual understanding of blockchain technology, its potential applications in digital payments, and its relevance within the context of India Stack. Research outcome: The study concluded that rising internet users and adoption of technology by the financial institutions and banking sector transformed the India as fastest growing economy in terms of digital payment systems.
Sabam Parjuangan, Suhardi -, I Gusti Bagus Baskara Nugraha
Small and medium enterprises (SMEs) require secure, efficient, and low-cost digital transaction systems. However, many blockchain-based platforms are designed for large-scale applications and impose significant computational overhead, making them unsuitable for resource-constrained SMEs. This study proposes a lightweight smart contract blockchain platform tailored for SME-scale service environments. The system implements a modular smart contract architecture integrated with a lightweight blockchain and automates key transactional processes, including balance top-ups, service ordering, order confirmation, and payment execution, while ensuring data integrity through a simplified Proof-of-Work mechanism. System performance is evaluated using a Design of Experiment (DOE) framework with a full factorial design and analyzed through Analysis of Variance (ANOVA). The results show that execution time remains below 5 seconds under workloads of up to 20 concurrent transactions, with CPU utilization below 55%. ANOVA results indicate that transaction concurrency and smart contract complexity significantly affect performance, while block size has a limited impact. Security evaluation confirms resistance to unauthorized access, double-spending, and reentrancy attacks.
Shihab Sarar, Ali Imran Mehedi, Fabbiha Tahsin Prova, Saha Reno
The modern metropolis essentially demands the use of stateâofâtheâart, realâtime surveillance systems, which should be reliable, scalable, and respectful of privacy at the same time. Critical shortcomings in traditional architectures are single points of failure, poor scalability, frequent data breaches, and inadequately managed privacy. These aspects of themselves make it inept for the demands of dynamic, fastâpaced city environments, without which reliability, security, and adaptability cannot be compromised at any cost. This brings to light the critical need for innovative and decentralized solutions that can overcome these challenges comprehensively. In our proposed approach, a decentralized framework integrates private blockchain technology via Ethereum, a hybrid cryptography model combining advanced encryption standard (AES) and RivestâShamirâAdleman (RSA) encryption, and stateâofâtheâart deep learning techniques such as YOLOv8, DeepSort, and ArcFace. Blockchain technology ensures metadata is immutable and transparent, thus saving metadata from unauthorized access and tampering. The hybrid cryptography model encrypts sensitive data through AES and securely shares the key of AES through RSA encryption, while decryption is efficiently done in a key management system (KMS). Furthermore, YOLOv8 and DeepSort can be used for highâprecision object detection and realâtime tracking, and ArcFace can be used for facial recognition, meeting the splitâsecond decisionâmaking required in urban surveillance. Extensive experiments are performed, and the results indicate that the proposed framework enhances detection precision, tracking accuracy, realâtime responsiveness (60 FPS), and resistance to tampering (>99% chain quality per quorum Byzantine fault tolerance [QBFT]) without compromising efficiency. The adaptive and reliable solution meets modern urban surveillance demands that are evolving at an everâincreasing pace. The scalability of the operation further ensures enhanced public safety. This paper discusses a decentralized urban surveillance system that is both tamperâproof and secure using current blockchain technologies, InterPlanetary file system (IPFS), hybrid AESâRSA, and deep learning technologies to mitigate the risks of a traditional centralized system, such as data tampering and privacy violations. The system uses the Ethereum blockchain to provide immutable metadata, the IPFS protocol to create a fully distributed storage system of video and image frames, and an offâchain KMS service to distribute the keys to the authorized edge devices. The system utilizes realâtime object detection (YOLOv8), tracking (DeepSort), and face recognition (ArcFace) to perform inference locally on the edge devices. We have performed experiments that demonstrate the tamperâproof and secure scalability with low latency and secure tamperâproof data integrity of this urban surveillance system in everâchanging urban environments.
This thesis presents a comprehensive predictive maintenance system and application interface that integrates deep learning and blockchain technologies in order to enhance maintenance strategies in industrial systems. Traditional predictive maintenance systems have significant issues regarding data security and decentralization. This study aims to address these limitations by leveraging blockchain technology, with a specific focus on improving the reliability and verifiability of predictive maintenance processes. In this study, an LSTM-CNN hybrid model was developed to evaluate complex patterns in both time and features, thereby enabling high-accuracy fault prediction. The proposed model is designed to perform binary classification for fault prediction in industrial equipment. During the implementation phase of the study, an open-source dataset was used to train and test the developed model. The Randomized Search method was used in the hyperparameter optimization process to increase the prediction success of the proposed model. The hybrid model was trained with 5-fold cross-validation, and class weighting and threshold value optimization methods were applied to eliminate the class imbalance problem. In the threshold optimization phase, F1-score-based methods are applied to maximize recall at three predefined minimum precision levels (0.05, 0.2, and 0.85), while identifying the most balanced trade-off between precision and recall. In the proposed system, sensor data are stored in a database (SQLite3), and cryptographic proofs generated using zero-knowledge techniques are transmitted to the Ethereum network. The Poseidon hash function is used to ensure data integrity, and the Groth16 protocol is used for Zk-Snark proof generation. This approach enables secure verification of data validity without publicly disclosing sensor data and simultaneously addresses scalability concerns. The system architecture is designed to include manager, operator, and engineer nodes, and all smart contracts are implemented using Solidity. In addition, a graphical user interface is developed using the Tkinter library in Python. The experimental results demonstrate that the proposed LSTMâCNN hybrid model produces successful outcomes in terms of fault prediction performance. According to scenario where the decision threshold is optimized based on the F1-score, the model achieves an accuracy of 0.987, an AUC value of 0.979, and an F1-score of 0.794. In future studies, the proposed system is planned to be implemented on the Ethereum mainnet instead of a test network, with a comprehensive evaluation of on-chain operational costs. However, instead of Zk-Snark proofs, which have a centralized structure, the use of Zk-Stark proofs, which are transparent and do not violate the principle of decentralization, is planned.
Background: The inherent immutability of traditional blockchain technology fundamentally conflicts with the need for dynamic updates and secure sharing of medical data. Existing editable blockchain solutions also face limitations in update efficiency, key management security, and cross-institutional privacy protection. Objective: This paper aims to design a novel architecture that integrates chameleon hash with a permissioned blockchain to achieve secure, efficient, and auditable incremental updates and controlled sharing of medical data. Methods: We propose a hybrid architecture comprising: (1) a lightweight off-chain update protocol based on chameleon hash, enabling authorized institutions to swiftly modify off-chain data using a trapdoor key while only recording lightweight credentials on the blockchain; (2) a distributed trapdoor key management mechanism based on threshold signatures, which disperses critical authority across multiple trusted medical nodes to eliminate single points of failure; and (3) cross-institutional data sharing smart contracts with privacy protection, featuring an integrated Zero-Knowledge Proof (ZKP) verification interface that allows third parties to verify data validity without accessing the original sensitive information. Results: Compared to traditional schemes, our method improves update throughput by 3.2Ă and reduces on-chain storage by 76%. Authorized updates and verification complete within 5 seconds in simulated cross-hospital scenarios, while distributed key management prevents unauthorized modifications. Conclusion: The proposed scheme balances dynamic updates with trustworthy auditing in medical data management. By addressing efficiency, security, and privacy limitations of existing solutions, it supports the development of a trusted, privacy-secure medical data ecosystem.