<b>Abstract.</b>Smart contract vulnerabilities have led to losses exceeding billions of US dollars in the decentralised finance (DeFi) ecosystem. Existing detection tools based on symbolic execution and static analysis, while precise, are computationally expensive and often impractical for large-scale screening. In this work, we propose a lightweight machine learning approach that operates directly on compiled EVM bytecode, requiring neither source code nor contract ABI. We design a feature engineering pipeline that extracts 65 security-oriented numerical features from disassembled bytecode instructions, covering reentrancy patterns, arithmetic overflow indicators, gas-based denial-of-service risks, access control anomalies, and environmental dependencies. Using a dataset of 117,091 real-world Ethereum smart contracts labelled by the Slither static analyser, we evaluate four classifiers—Logistic Regression, Decision Tree, Random Forest, and XGBoost—under stratified 5-fold cross-validation. XGBoost, optimised via Bayesian hyperparameter search (Optuna, 50 trials), achieves an F1-score of 0.947 on cross-validation and 93% accuracy on a held-out validation set, with 0.97 recall for vulnerable contracts and 0.85 recall for safe contracts. We additionally benchmark text-based opcode sequence representations and find that hand-crafted numerical features substantially outperform n-gram vectorisation approaches.<br>Code and materials (GitHub): https://github.com/SergeySolovyev/Machine-Learning-Based-Vulnerability-DetectionDate: 26 Feb 2026. Version: v1.
Tourism transactions face persistent challenges related to transparency, security, and dependence on online travel agents (OTAs), which reduce local providers' margins and limit direct customer engagement. Existing blockchain-based tourism solutions remain fragmented and often lack modularity and platform-agnostic integration. This study proposes SmartTourismChain (STC), a modular smart contract architecture deployed on the Ethereum Sepolia test network. STC is designed as a plug-in framework supporting cross-platform adoption through interoperable APIs and SDKs, with backend services for reservation, verification, and nonce management, and frontend integration via wallet connection or Sign-In with Ethereum (SIWE). The architecture supports dual transaction modes, enabling fast off-chain operations while maintaining auditable on-chain records. Functional validation demonstrates a 100% success rate for booking execution, token transfer, and QR-based verification. On-chain deployment records a gas consumption of 175,550 gas ($\approx 0.00026$ETH), indicating technical and economic feasibility. Security analysis confirms resistance to common smart contract vulnerabilities, including reentrancy and unauthorized state manipulation. Overall, STC reduces OTA dependency and supports the development of decentralized, IoT-ready digital tourism ecosystems.
Modern precision agriculture depends on safe and effective fertilizer management. However, existing systems lack real-time decision-making capabilities, rarely incorporate secure traceability methods, and mainly concentrate on nutrient prediction without determining the type of soil fertilizer utilized for a specific crop. To classify fertilizer types (organic vs. inorganic) in real-time based on soil nutrient parameters (temperature, pH, EC, N, P, and K), this investigation suggests an innovative, lightweight self-attention transformer neural network (TNN) based Fertilizer class contract network (FCCN) model. The proposed research is one of the first to combine secure blockchain recording, fertigation, and fertilizer-type detection into a single edge-based pipeline that operates in real time. The process integrates blockchain-based transaction logging and IoT-edge computing for recording transparent and secure agricultural activity. Whenever deficits emerge, the suggested method uses Venturi irrigation to automatically activate fertigation after processing real-time sensor data at the edge to determine the types of fertilizer utilized and the nutritional status. This work uses a decentralized and scalable architecture compared to cloud-dependent or AI-based-only models. Fertilizer classification and fertigation actions based on the real-time nutrient level recommendation are recorded as immutable transactions on an Ethereum blockchain using a Proof-of-Stake (PoS) consensus. Before the final on-chain recording, validator logic confirms the accuracy of field data, fertigation events, and real-time soil nutrient levels. Real-time blockchain measurements reveal transaction completion speeds of less than 0.03 seconds, gas consumption of less than 62,000 units, and throughput of 15-35. Experimental findings show that FCCN categorization accuracy surpasses 98.85%.
Dynamic-weight AMMs (aka Temporal Function Market Makers, TFMMs) implement algorithmic asset allocation, analogous to index or smart beta funds, by continuously updating pools' weights. A strategy updates target weights over time, and arbitrageurs trade the pool back toward those weights. This creates a sequence of small, predictable mispricings that grow until taken, effectively executing rebalances as a series of Dutch reverse auctions. Prior theoretical and simulation work (Willetts & Harrington, 2024) predicted that this mechanism could outperform CEX-style rebalancing. We test that claim on two live pools on the QuantAMM protocol, one on Ethereum mainnet and one on Base, across two short rebalancing windows six months apart (July 2025 and January 2026). We perform block-level arbitrage analysis, and then measure long term outcomes using Loss-vs-Rebalancing (LVR) and Rebalancing-vs-Rebalancing (RVR) benchmarks. On mainnet, rebalancing becomes markedly more efficient over time (more frequent arbitrage trades with lower value extracted per trade), reaching performance comparable to or better than CEX-based models. On Base, rebalancing persists even when per-trade extraction is near (or below) zero, consistent with routing-driven execution, and achieves efficiencies that meet or exceed standard "perfect rebalancing" LVR baselines. These results demonstrate dynamic-weight AMMs as a competitive execution layer for tokenised funds, with superior performance on L2s where routing and lower data costs compress arbitrage spreads.
Zhaohuang Chen, Zhongqi Fu, Tao Liang, Haidong Ma · 6 authors
Abstract Since the proposal of the blockchain, its application scenarios have been continuously expanded. However, the anonymity feature of the blockchain has hindered market regulation, leading to numerous illegal activities such as phishing fraud, which has now become a serious type of crime. Currently, most phishing fraud detection technologies on blockchain platforms use transaction data to construct basic raw transaction graphs and then use neural network methods to mine key information. This study proposes a graph gated recurrent neural network (GGRNN) model that fully integrates temporal and spatial information, effectively utilizing time-related information in the transaction graph. It first takes an account as the center node to obtain its second-order transaction data and then constructs a dynamic transaction graph (DTG). Subsequently, the DTG is fed to the GGRNN to process the temporal features in a gated recurrent unit (GRU) framework and introduce graph convolutional network (GCN) operations to fully use the node neigh-bourhood topology features, obtain the embedded representation of the graph, and then perform graph classification for phishing node detection. To verify the effectiveness of the proposed model, it was applied to real-world Ethereum transaction datasets. Numerical results show that the proposed GGRNN model significantly outperforms state-of-the-art methods.
The proliferation of cloud infrastructures has intensified concerns regarding data security, integrity, identity and access management, and user privacy. Despite recent advances, existing solutions often lack comprehensive integration of privacy-preserving mechanisms, dynamic trust management, and cross-provider interoperability. This study proposes an AI-enabled, zero-trust, blockchain-fused identity management framework for secure, privacy-preserving multi-cloud environments. The framework integrates homomorphic encryption with differential privacy for aggregate-level protection and secure multi-party computation for collaborative data processing. The proposed system was validated in a simulated multi-cloud environment using CloudSim, Ethereum blockchain, and AWS EC2. Experimental results indicate homomorphic encryption latency of approximately 450ms per operation and statistically significant security improvements (t(128) = 12.47, p < 0.001), privacy (t(95) = 8.93, p < 0.001), and throughput (t(156) = 15.21, p < 0.001). The framework achieved differential privacy with ε = 0.1 while retaining 99.2% data utility, and demonstrated a 34% improvement in processing speed over conventional differential privacy approaches. In addition, the implementation was observed to be 2.3× faster than BGV-based configurations, with 45% lower memory consumption than CKKS and a 67% reduction in ciphertext size relative to baseline implementations. From an operational perspective, the framework shows a 23% reduction in security management costs, a 31% improvement in resource utilization efficiency, and an 18% decrease in compliance audit expenses. The model further indicates a 27% reduction in total cost of ownership (TCO) compared with multi-vendor security solutions, a projected return on investment (ROI) within 14 months, and an 89% reduction in security incident response costs under the evaluated conditions.
Anthony Uchenna Eneh, Love Allen Chijioke Ahakonye, Jae Min Lee, Dong-Seong Kim
Modern auto-insurance workflows require sharing heterogeneous digital evidence across multiple organizations. Yet, current cloud-based role-based access control mechanisms remain coarse-grained and poorly suited for expressing time, purpose, and case-specific constraints. This study presents ClaimGuard, which addresses these limitations by placing a blockchainbacked attribute-based access control gateway in front of existing evidence stores, enforcing fine-grained on-chain policies, and issuing short-lived capability tokens for authorized access. Implemented as a REST gateway with PureChain smart contracts, ClaimGuard is evaluated using realistic workloads involving up to 200 subjects and 1000 evidence resources. Experiments on a local Ethereum network shows sub$\sim 70 ~\text{ms}$tail latency, throughput exceeding$\sim 1000$requests/s, rapid policy updates, and zero false accepts, demonstrating the practicality of decentralized, auditable access control for privacy-preserving claims evidence sharing.
Hamid Najafi Bouyaghchi, Ameneh Farahani, Ismail A Mageed
The cryptocurrency market is volatile, which makes it very difficult to accurately predict. The Long Short-Term Memory (LSTM) is an approach to Predict Price Cryptocurrency (PPC) that uses price time series data. However, in this method, the prediction accuracy is dependent on the tuning of meta-parameters. Therefore, to tune these meta-parameters, an improved version of the optimization algorithms is needed that provides the task of selecting the optimal values of these parameters for price predictions. Therefore, in this study, the LSTM is combined with the classic version of the Differential Evolution (DE) algorithm, and the real data against the prediction results of the model presented in this study showed the appropriate accuracy of this model. Then, the classic version of the DE algorithm was modified to reduce its errors compared to previous algorithms. In this regard, coding was done in MATLAB version 2023b software, and the improved version was compared in terms of error rate with the Gray Wolf Optimizer (GWO), Particle Swarm Optimization (PSO), Genetic Algorithm (GA), and the new Bald Eagle Search (BES) algorithm, which showed an accuracy of 86.94% for the improved model in this study.
SARMF (Smart Contract Automated Remediation and Mitigation Framework) is a structured and reproducible security engineering pipeline designed for vulnerability detection, taxonomy alignment, automated remediation, and adversarial validation of Ethereum-compatible smart contracts. This operational protocol presents a structured workflow for smart contract vulnerability detection and automated mitigation within blockchain-based systems. The methodology integrates deterministic environment setup, multi-tool static analysis, vulnerability normalization using standardized taxonomies, rule-based automated patch generation, and dynamic adversarial validation. By combining static detection tools with controlled refactoring patterns and behavioral verification, the framework ensures reproducibility, traceability, and measurable performance impact assessment. The protocol concludes with comprehensive audit reporting and archival procedures to support transparency and independent verification. This workflow provides a systematic foundation for secure smart contract lifecycle management in decentralized applications. Unlike traditional audit checklists, this framework operationalizes vulnerability detection, taxonomy alignment, automated remediation generation, and validation feedback loops into a unified reproducible security engineering pipeline. Key Contributions of SARMF: Deterministic environment and compilation reproducibility model. Unified multi-tool vulnerability normalization aligned with SWC taxonomy. Rule-based automated mitigation generation preserving semantic integrity. Iterative validation loop combining static, adversarial, and fuzz testing. Structured audit archival enabling independent verification and traceability.
The sudden growth of cryptocurrencies has created a set of intricate regulatory and legal issues for the financial and governance system of India. The decentralized nature of digital currencies like Bitcoin and Ethereum challenges the conventional monetary system, giving rise to concerns about their legal status, protection of investors, taxation, and overall financial stability. This paper critically analyzes the regulatory environment in India, especially in the wake of the 2018 circular issued by the Reserve Bank of India and its subsequent strike-down in the case of Internet and Mobile Association of India v. Reserve Bank of India. It also discusses challenges with respect to money laundering under the Prevention of Money Laundering Act, 2002, taxation of virtual digital assets, and the lack of a comprehensive statutory regulatory framework for cryptocurrency exchanges. The paper contends that the current stance of India is one of regulatory ambivalence, vacillating between control and tolerance.
A.S. Kannan, E. Baraneetharan, R.Venkatasubramanian, S. Sasi · 6 authors
India's ambitious renewable energy targets of 500 GW by 2030 and net-zero emissions by 2070 necessitate transformative energy trading solutions capable of harnessing distributed renewable sources. This paper introduces a blockchain-enabled peer-to-peer (P2P) energy trading platform designed for India's diverse energy landscape, which includes rooftop solar, wind plants, and microgrids in both urban and rural areas. Built on the Ethereum foundation, the platform employs smart contracts to automate energy transactions between prosumers, reducing dependence on the conventional grid and advancing India's energy security goals. The system integrates machine learning algorithms trained on specific Indian usage patterns and weather conditions to forecast optimal trading times, accounting for seasonal changes, festivals, and industrial demand cycles. Key model assumptions include: (i) prosumers have bidirectional smart meters with IoT connectivity; (ii) weather data availability from Indian Meteorological Department stations; (iii) baseline electricity tariffs following state-level regulatory frameworks; and (iv) participants operate within Karnataka Electricity Regulatory Commission's P2P trading guidelines. Core parameters include LSTM networks with 50 hidden units, learning rate of 0.001, and 24-hour prediction horizons; Random Forest models with 100 estimators and maximum depth of 10; smart contract gas limits of$3,000,000$units; and dynamic pricing coefficients$\alpha=0.15$and$\beta=0.08$calibrated against Tamil Nadu industrial tariffs. Through automated transactions, the platform allows small-scale generators to sell surplus energy directly to local consumers, mitigating the$18-20 \%$distribution losses typical of the Indian grid. Pilot studies in Tamil Nadu and Maharashtra showcased significant results, including a 35-45% cost saving for participating industries and transparent carbon credit accounting, aligning with emerging ESG compliance needs. The platform contributes to the Digital India initiative by fostering a decentralized energy infrastructure that supports both economic development and environmental sustainability.
Ethereum transaction fees exhibit substantial shortterm volatility driven by network congestion, making it difficult for users and applications to determine optimal transaction timing. This work investigates the temporal structure of Ethereum base fees and develops a scalable data-collection and forecasting pipeline for short-horizon, congestion-aware fee estimation. We propose a harvester engine framework based on a parallel blockprocessing mechanism to capture short-term market volatility and develop a parallelized harvester for efficient fee-history collection using the eth_feeHistory JSON-RPC interface. This interface provides the high-resolution, block-level data required for intraday analysis, despite protocol constraints such as the$\mathbf{1 0 2 4}$-block retrieval limit per request. Our fee-history engine incorporates bounded concurrency, latency-aware pacing, and retry stabilization, reducing 30-day data-acquisition time from hours to minutes. We analyze intra-day fee behavior and show that Ethereum base fees exhibit a stable$\mathbf{2 4}$-hour diurnal cycle. We also propose a normalized shape with a rolling-level calibration framework that preserves a stable daily rhythm while continuously adapting to month-level fee changes. Empirical evaluation shows that the adaptive approach improves accuracy and robustness. These findings demonstrate that Ethereum gas fees contain a predictable structure that can be leveraged for practical, short-term forecasting when combined with adaptive calibration.
ABSTRACT The digitization of healthcare insurance claims faces persistent challenges including data breaches, fraudulent submissions, and inefficiencies in verification and settlement. This paper presents a Zero‐Knowledge Succinct Non‐Interactive Argument of Knowledge (Zk‐SNARK) enabled blockchain framework deployed on the Polygon Proof of Stake (PoS) network for secure and privacy‐preserving health insurance processing. The proposed architecture integrates Attribute‐Based Encryption (ABE) for data confidentiality and the Elliptic Curve Digital Signature Algorithm (ECDSA) for authentication, ensuring end‐to‐end data integrity and access control. Experimental evaluation on the Polygon PoS testbed demonstrates a transaction cost of approximately $0.002, which is over 99% lower than Ethereum's 3–10 $ per transaction, while maintaining 100% resistance to data tampering, replay attacks, and transaction manipulation. Under the Polygon real network, the proposed framework supports a network‐level transaction capacity of up to 7000 transactions per second (TPS) under nominal operating conditions, with an approximately 9.3% reduction in effective capacity under stress scenarios, while maintaining 100% verification accuracy for all Zk‐SNARK proofs. The average on‐chain verification and settlement latency was measured at 4.7 s, confirming the system's suitability for real‐time healthcare claim settlement. These results validate that the proposed Zk‐SNARK enabled Polygon PoS framework offers a scalable, cost‐efficient, and cryptographically robust solution for healthcare insurance automation, outperforming existing blockchain implementations across security, efficiency, and economic performance metrics.
Everybody is these days plunging into decentralized applications, blockchain, and digital identity. And honestly, it's a rendering that the ancient method of authenticating yourself looks nice, outdated and risky. Whenever you give up your personal info, you are just wishing it does not find its way into a data leak or get misused. Precisely, this is the reason that we constructed a new path to manage identity checks that really care about your privacy. This is what we are doing: our framework is based on Ethereum Attestation Service (EAS) and Zero-Knowledge Proofs (ZKPs). To begin with, we generate offchain attestations based on the EIP-712 standard. Your signature remains verifiable; however, your confidential information doesn't go anywhere and through which we squeeze these attestations. SP1 using zero-knowledge virtual machine (zkVM) this step checks everything twice, the construction, the encryption, the logic, all of it. When it's all good then the system will spit a short, non-interactive Groth16 or Plonk (if)SNARK proofs known as zero-knowledge proofs (you're curious). This evidence makes things private and at the same time accurate. There is the interesting side of it: you can check it immediately in your local devices using a super lightweight browser or with a Node.js app WebAssembly verifier. It does not require any middlemen and there is no need for extra trust. You can send evidences, in case you wish to using Solidity contract on-chain. This allows the system to issue new fraudulent statements such as isOver18 = true without displaying your actual age or any other personal data. So what does this mean? You earn greater confidence, enhanced interoperability and connections through decentralize systems. Transparency is what you have with this of ZKP attestation and actual privacy. It's actually practical, as well, can be used with KYC, DeFi, age-requiring app checks, and secured access controls. Essentially, it is a huge leap higher on behalf of anonymity and trust in electronic self.
This research demonstrates the environmental impacts of Digital Currencies (DC), particularly focusing on Bitcoin's (BTC) energy-intensive Proof-of-Work (PoW) process as well as a fundamental expectation for sustainable alternatives, which can be termed as Green Coins (GC) which are expected to be able to maintain the benefits of BTC, while generating little to no negative impacts on the environment. Bitcoin is estimated to consume about 150 TWh annually, a measure comparable to that of a mid-sized country, while also generating 60 to 90 million metric tons of$\text{CO}_{2}$emissions and about 30,000 metric tons of electronic waste (e-waste) through deliberate accelerated hardware obsolescence. On the other hand, GC tends to use more efficient proofs such as Proof of Stake (PoS) and Proof of Space-time (PoST) and examples include Ethereum following its 'Merge' estimated a reduction of over 99 % of energy use and Dogecoin has and even lower environmental impact compared to BTC. Using data sets from the Cambridge Bitcoin Electricity Consumption Index (CBECI) and Digiconomist, this study quantifies Bitcoin's carbon footprint and tracks the trends from 2017 to 2025, through more extensively investigating its sustainability profile relative to its GC counterparts. Findings reveal Bitcoin continues to have high energy use and e-waste, peaking in 2021, while both Ethereum (ETH) and Dogecoin (DG) had significant gains in sustainability improvements. Addressing scaling, security, and regulatory issues, the paper highlights the potential of sustainable financing within the digital financial markets to drive Green technologies, which is increasingly important for aligning cryptocurrency financing with Environmental, Social, and Governance (ESG) parameters, providing a way to continue to innovate while decarbonizing digital financing.
In democratic systems, secure and transparent voting mechanisms are essential to maintain public trust and electoral integrity. Traditional paper-based and centralized electronic voting systems often face challenges such as limited transparency, risk of data manipulation, and dependence on centralized authorities. To address these issues, this project proposes a decentralized blockchain-based voting system designed to enhance security, transparency, and reliability. The system is developed on the Ethereum blockchain, where each vote is recorded as an immutable transaction to prevent tampering or duplication. Smart contracts written in Solidity automate essential election functions including voter registration, vote validation, and result computation. A web-based interface built using React.js and Web3.js enables secure interaction with the blockchain, while wallet-based authentication ensures that each authorized user can cast only one vote The system is implemented and tested in a controlled environment to evaluate performance, accuracy, and resistance to double voting.
Global illicit fund flows exceed an estimated $3.1 trillion annually, with stablecoins emerging as a preferred laundering medium due to their liquidity. While decentralized protocols increasingly adopt zero-knowledge proofs to obfuscate transaction graphs, centralized stablecoins remain critical transparent choke points for compliance. Leveraging this persistent visibility, this study analyzes an Ethereum dataset to establish an empirical baseline for behavioral AML detection. Our findings demonstrate that domain-informed tree ensemble models achieve higher Macro-F1 score, significantly outperforming graph neural networks, which struggle with the increasing fragmentation of transaction networks. The model's interpretability goes beyond binary detection, successfully dissecting distinct typologies: it differentiates the complex, high-velocity dispersion of cybercrime syndicates from the constrained, static footprints left by sanctioned entities. This methodological approach provides actionable insights that align with industry shifts toward deterministic verification, informing the auditability and compliance requirements under regulations such as the EU's MiCA and the U.S. GENIUS Act while minimizing unjustified asset freezes. By providing a high-precision behavioral classification of suspicious wallets, this approach contributes to raising the economic cost of financial misconduct while informing compliance practice under emerging stablecoin regulations.
Smart contracts, primarily written in Solidity, are Turing-complete programs on platforms like Ethereum, requiring gas fees for deployment and execution. Gas quantifies computational costs, and inefficient contracts result in unnecessary expenses for developers and users. Gas optimization at the source code level has been studied in various related works; however, existing methods for summarizing gas-inefficient patterns primarily rely on author-defined rules or heuristic approaches, and their evaluations lack a labeled dataset.In this paper, we conduct a comprehensive empirical study on the issue of gas optimization in smart contracts. We begin by gathering audit reports from Code4rena, a well-known smart contract audit platform. These reports include both expert evaluations, conducted by professionals known as Wardens, and automated analyses generated by the platform’s static analysis tool, 4naly3er. After filtering out false-positive gas optimization instances from the automated reports, we identify 2,095 instances of gas-inefficient patterns across 54 projects. We categorize these inefficiencies into 24 types using thematic analysis and find that static analysis tools often produce false positives and negatives. To address this, we propose a hybrid method combining static analysis and large language models (LLMs) to detect and repair gas inefficiencies. The static analysis tool identifies potential optimization opportunities, while the LLM refines these findings and suggests effective repairs. Our evaluation shows that our approach achieves a precision rate of 82.28% and a recall rate of 88.46%, and can save 919 units of gas per function on average during execution.
Najaf Iqbal, Muhammad Abubakr Naeem, Hang Luo, Walid Bakry
Using 5-minute data of 16 cryptocurrency tokens belonging to 5 different categories (AI, Gaming, Meme, Layer 1/2, and FAN tokens), we investigate the risk transmission in higher moments, i.e. realized volatility (RV), realized skewness (RS), and realized kurtosis (RK), employing the TVP-VAR framework and robustness tests. We also perform six sub-sample investigations on various geopolitical and other systemic events. Ethereum, Binance Coin, and Ripple are strongly related to other tokens. Sandbox, Decentraland, and Enjin Coin lead spillover transmission, while Numeraire, Measurable Data Token, and Cryptex Finance absorb most of the shocks. The connections are stronger regarding RV than RS and RK, showing potential for tail-risk reduction, which is heterogeneous regarding extreme events. AI tokens are the least connected during normal conditions as well as most of the extreme events, except the US presidential Election, which puts these tokens in the centre of the system. The Israel-Palestine war, the FTX collapse, and the SEC approval of the first Bitcoin ETF are among the most important events regarding enhancement in the higher-moment risk transmission. Token market investors/traders and regulators can draw essential insights from our findings.
Zibin Lin, Taotao Wang, Shengli Zhang, Long Shi · 6 authors
Open Web 3.0 platforms increasingly operate as \emph{service ecosystems} (e.g., DeFi, DAOs, and decentralized social applications) where \emph{admission control} and \emph{account provisioning} must be delivered as an always-on service under bursty demand. Service operators face a fundamental tension: enforcing Sybil resistance (one-person-one-account) while preserving user privacy, yet keeping on-chain verification cost and admission latency predictable at scale. Existing credential-based ZK admission approaches typically require per-request on-chain verification, making the provisioning cost grow with the number of concurrent joiners. We present \textbf{ZK-AMS}, a scalable admission and provisioning layer that bridges real-world \emph{Personhood Credentials} to anonymous on-chain service accounts. ZK-AMS combines (i) zero-knowledge credential validation, (ii) a \emph{permissionless} batch submitter model, and (iii) a decentralized, privacy-preserving folding pipeline that uses Nova-style recursive aggregation together with multi-key homomorphic encryption, enabling batch settlement with \emph{constant} on-chain verification per batch. We implement ZK-AMS end-to-end on an Ethereum testbed and evaluate admission throughput, end-to-end latency, and gas consumption. Results show stable verification cost across batch sizes and substantially improved admission efficiency over non-recursive baselines, providing a practical and cost-predictable admission service for large-scale Web 3.0 communities.