In recent years, blockchain consensus mechanisms have evolved significantly from the original proof-of-work design, transitioning towards more efficient and scalable alternatives. This paper presents a comprehensive review and analysis framework for blockchain consensus mechanisms based on a systematic examination of 200+ publications. We categorize consensus mechanisms into four performance-oriented groups: high throughput, strong security, low energy, and flexible scaling, each addressing specific trade-offs in the blockchain trilemma of decentralization, security, and scalability. Through quantitative metrics including transactions per second, energy consumption, fault tolerance, and communication complexity, we evaluate mainstream mechanisms. Our findings reveal that no single consensus mechanism optimally satisfies all performance requirements, with each design involving explicit trade-offs. This paper provides researchers and practitioners with a structured framework for understanding these trade-offs and selecting appropriate consensus mechanisms for specific application contexts. Finally, we discussed future development trends, as well as regulatory and ethical considerations.
This paper introduces a pioneering multi-layered cybersecurity framework for Decentralized Finance (DeFi) platforms, fundamentally transforming traditional financial infrastructure by operating without centralized intermediaries through blockchain-based smart contracts, creating unprecedented accessibility while simultaneously introducing complex security challenges requiring specialized defense mechanisms. The immutable nature of blockchain technology necessitates comprehensive proactive security measures, as deployed smart contracts cannot be easily modified to address discovered vulnerabilities. Multi-layered security frameworks encompass pre-deployment foundations, including rigorous smart contract auditing by multiple independent firms, formal verification processes that mathematically prove contract behavior alignment with intended specifications, and transparent code documentation enabling thorough community security reviews. Runtime protection mechanisms incorporate time-locks enforcing mandatory delays before implementing critical protocol changes, circuit breakers serving as emergency stops when suspicious activity is detected, and rate limiting controls preventing flash loan attacks through transaction volume restrictions. Access control systems utilize multi-signature wallets requiring multiple authorized parties for transaction approval, while progressive decentralization strategies enable structured transitions from centralized development teams to distributed community governance. Financial protection frameworks integrate insurance protocols providing coverage against successful exploits, treasury management systems maintaining reserve funds through secure multi-signature mechanisms, and comprehensive risk management frameworks enabling continuous monitoring and threat identification. Community-driven security initiatives leverage distributed expertise through bug bounty programs offering competitive rewards for responsible vulnerability disclosure, collaborative security reviews identifying issues missed by formal auditing, and educational programs enhancing user awareness of security best practices and threat recognition capabilities.
The integration of blockchain technology into decision support systems (DSS) represents a paradigm shift in how organizations approach data integrity, transparency, and collaborative decision-making processes.This research explores the fundamental mechanisms through which blockchain technology enhances traditional DSS architectures, focusing on distributed ledger capabilities, consensus mechanisms, and cryptographic security features.The study examines various implementation frameworks, analyzing their effectiveness in real-world applications across multiple industrial sectors including healthcare, supply chain management, and financial services.Through comprehensive analysis of existing blockchain-based DSS implementations, this paper identifies key advantages such as immutable data records, enhanced transparency, reduced intermediary costs, and improved stakeholder trust.The research methodology encompasses both theoretical framework development and empirical evaluation of blockchain-DSS integration models.Critical challenges including scalability limitations, energy consumption concerns, and regulatory compliance issues are thoroughly investigated.The findings reveal that while blockchain technology significantly improves data reliability and system transparency in DSS environments, implementation requires careful consideration of technical constraints and organizational readiness.Performance metrics demonstrate measurable improvements in decision accuracy, audit trail completeness, and stakeholder confidence levels.The study concludes with recommendations for optimal blockchain-DSS integration strategies, highlighting the importance of hybrid approaches that combine traditional centralized processing with distributed ledger benefits.Future research directions include investigation of quantum-resistant blockchain protocols and artificial intelligence integration within blockchain-based decision support frameworks.This work contributes to the growing body of knowledge on distributed systems applications in organizational decision-making processes.
Open access
Blockchain Technology Applications and Security
Economic and Technological Systems Analysis
Advanced Research in Systems and Signal Processing
Decentralized blockchain payment infrastructures are rapidly emerging as transformative tools for reshaping financial transactions in the United States.Traditional payment systems remain heavily reliant on intermediaries such as banks, card networks, and clearinghouses, which impose significant transaction fees and introduce settlement delays.These inefficiencies disproportionately affect small businesses, underbanked populations, and cross-border remittances, where costs and time lags create barriers to broader participation in the financial ecosystem.Blockchain-based payment systems, by contrast, utilize distributed ledgers and smart contracts to enable peer-to-peer transactions with reduced reliance on intermediaries.This structural shift holds the potential to substantially lower transaction fees, streamline settlement processes to near-real-time, and enhance transparency through immutable record-keeping.From a broader economic perspective, decentralized payment solutions align with the growing demand for financial inclusion and democratized access to capital flows.They allow micro-entrepreneurs, gig workers, and rural communities to participate more effectively in economic activities by reducing entry costs and providing verifiable transaction histories.In the U.S. context, the integration of blockchain into mainstream finance could complement existing systems such as ACH, FedNow, and card-based networks, while offering alternatives that better serve marginalized groups.Narrowing the focus, evidence suggests that fintech innovators piloting blockchain platforms have already demonstrated measurable reductions in processing costs and settlement times for retail and institutional payments alike.Nonetheless, challenges persist in terms of regulatory clarity, interoperability with legacy infrastructures, and concerns over scalability and energy use.Addressing these issues through targeted policy reforms and publicprivate partnerships will be critical to ensuring that decentralized blockchain payment infrastructures can deliver on their promise of inclusive, efficient, and secure economic participation.
Nan Wang, Nan Wu, Xiangyu Hui, Jiafan Wang · 5 authors
As the demand for exercising the "right to be forgotten" grows, the need for verifiable machine unlearning has become increasingly evident to ensure both transparency and accountability. We present {\em zkUnlearner}, the first zero-knowledge framework for verifiable machine unlearning, specifically designed to support {\em multi-granularity} and {\em forgery-resistance}. First, we propose a general computational model that employs a {\em bit-masking} technique to enable the {\em selectivity} of existing zero-knowledge proofs of training for gradient descent algorithms. This innovation enables not only traditional {\em sample-level} unlearning but also more advanced {\em feature-level} and {\em class-level} unlearning. Our model can be translated to arithmetic circuits, ensuring compatibility with a broad range of zero-knowledge proof systems. Furthermore, our approach overcomes key limitations of existing methods in both efficiency and privacy. Second, forging attacks present a serious threat to the reliability of unlearning. Specifically, in Stochastic Gradient Descent optimization, gradients from unlearned data, or from minibatches containing it, can be forged using alternative data samples or minibatches that exclude it. We propose the first effective strategies to resist state-of-the-art forging attacks. Finally, we benchmark a zkSNARK-based instantiation of our framework and perform comprehensive performance evaluations to validate its practicality.
В статье рассматриваются алгоритмы консенсуса как основа функционирования криптовалютных и блокчейн-систем. Раскрывается их экономическая и технологическая сущность, проводится сравнительный анализ основных моделей – Proof-of-Work (PoW), Proof-of-Stake (PoS), Delegated Proof-of-Stake (DPoS), Practical Byzantine Fault Tolerance (PBFT) и гибридных решений. Выделяются их преимущества и недостатки, определяется область применения и перспективы развития в условиях необходимости повышения масштабируемости, энергоэффективности и устойчивости к кибератакам. Особое внимание уделяется проблеме «триилеммы блокчейна» и поиску оптимального баланса между безопасностью, децентрализацией и производительностью. Сделан вывод о важности гибридных моделей и инновационных протоколов в формировании будущей архитектуры децентрализованных финансов.
Moisés Wladimir Henríquez-Moreira, Ariana Yomira Zamora-Párraga, Darwin Javier Zamora Mayorga
Participatory budgeting is presented as a tool for democratic governance that promotes citizen participation, transparency, and the equitable distribution of public resources through dialogue and consensus. The main objective of this research is to analyze the relationship between participatory budgeting and the management of the Decentralized Municipal Autonomous Government of the Ventanas canton during the year 2024, with two specific objectives: to determine how it strengthens local governance and to identify its impact on the canton's socioeconomic development. The methodology used was descriptive-explanatory with a qualitative approach, allowing for the characterization of the phases and actors involved in the process, as well as the examination of factors that influence its implementation. Documentary analysis of regulatory and bibliographic sources was used, along with interviews with officials from the GAD's Finance, Administration, and Planning departments, as well as with citizens, to learn about their perceptions and experiences. The participatory budget was developed in five phases: organization and dissemination, training, working groups, preparation and approval, and monitoring. Financial indicators revealed high efficiency in revenue (98%) and expenditure (97%), as well as a reduction in financial dependence. However, problems of socioeconomic disconnect and political prioritization were identified that limit the social impact of participatory budgeting, underscoring the need to strengthen planning and citizen participation.
Nicolò Romandini, Carlo Mazzocca, Kai Otsuki, Rebecca Montanari
Blockchain and smart contracts have garnered significant interest in recent years as the foundation of a decentralized, trustless digital ecosystem, thereby eliminating the need for traditional centralized authorities. Despite their central role in powering Web3, their complexity still presents significant barriers for non-expert users. To bridge this gap, Artificial Intelligence (AI)-based agents have emerged as valuable tools for interacting with blockchain environments, supporting a range of tasks, from analyzing on-chain data and optimizing transaction strategies to detecting vulnerabilities within smart contracts. While interest in applying AI to blockchain is growing, the literature still lacks a comprehensive survey that focuses specifically on the intersection with AI agents. Most of the related work only provides general considerations, without focusing on any specific domain. This paper addresses this gap by presenting the first Systematization of Knowledge dedicated to AI-driven systems for blockchain, with a special focus on their security and privacy dimensions, shedding light on their applications, limitations, and future research directions.
The InterPlanetary File System (IPFS) has been successfully established as the de facto standard for decentralized data storage in the emerging Web3. Despite its decentralized nature, IPFS nodes, as well as IPFS content providers, have converged to centralization in large public clouds. Centralization introduces BGP routing-based attacks, such as passive interception and BGP hijacking, as potential threats. Although this attack vector has been investigated for many other Web3 protocols, such as Bitcoin and Ethereum, to the best of our knowledge, it has not been analyzed for the IPFS network. In our work, we bridge this gap and demonstrate that BGP routing attacks can be effectively leveraged to censor content in IPFS. For the analysis, we collected 3,000 content blocks called CIDs and conducted a simulation of BGP hijacking and passive interception against them. We find that a single malicious AS can censor 75% of the IPFS content for more than 57% of all requester nodes. Furthermore, we show that even with a small set of only 62 hijacked prefixes, 70% of the full attack effectiveness can already be reached. We further propose and validate countermeasures based on global collaborative content replication among all nodes in the IPFS network, together with additional robust backup content provider nodes that are well-hardened against BGP hijacking. We hope this work raises awareness about the threat BGP routing-based attacks pose to IPFS and triggers further efforts to harden the live IPFS network against them.
The relevance of this article lies in the existence of over 13,000 decentralized autonomous organizations worldwide, with a total capitalization exceeding 23 billion USD. Numerous projects exploit this form to circumvent regulatory frameworks. At both the international and Ukrainian levels, a coherent understanding of the phenomenon of decentralized autonomous organizations, their objectives, genesis, and legal nature remains absent. The purpose of this article is to explore the genesis and legal nature of decentralized autonomous organizations – from the inception of the technical idea to their transformation into sui generis legal entities. Applying comparative and formal legal methods to examine the development of the legal understanding of these organizations, and employing case study methodology to assess their implementation in practice, the article investigates the main stages of the formation of the modern concept of decentralized autonomous organizations, their differentiation from adjacent constructs – decentralized applications, autonomous agents, and decentralized organizations – by highlighting criteria of autonomy and decentralization, along with case studies from Bitcoin to The DAO. On the basis of a comparative legal analysis of regulatory models in the United States, Europe, and offshore jurisdictions, a conceptual mismatch is identified between classical corporate forms and the ontology of decentralized autonomous organizations. A two-component qualification test is proposed, alongside a typology dividing them into genuine, hybrid, and quasi forms. The findings of the study, together with the identification of practical challenges faced by such projects, substantiate the possibility of recognizing decentralized autonomous organizations as legal persons under Ukrainian law by means of the doctrinal construct of the “personalized purpose” (Zweckvermögen) developed by A. von Brinz, potentially implemented in the form of a foundation. This approach permits the integration of algorithmic will with legal personality without undermining their decentralized nature. The article provides a foundation for further inquiries into specific legal characteristics of decentralized autonomous organizations, including the “sorites paradox” and the prospects for legislative regulation within the Ukrainian legal order based on the doctrine of personalized purpose.
Decentralized Finance (DeFi) is among the most revolutionary blockchain technology applications that changes how financial systems operate globally by eliminating the middlemen and allowing peer-to-peer transactions via smart contracts. DeFi platforms built on decentralized networks recreate core banking services (e.g., lending, borrowing, trading, and asset management) in a transparent, borderless, and programmable setting. This paper looks at the ways in which DeFi is disrupting conventional banking and the regulation issues that have emerged due to the phenomenon. It discusses the technical foundations of DeFi, its benefits of inclusiveness, efficiency, and innovation and its risks of volatility, security, and systemic vulnerability. Among the major regulatory issues identified in the paper are jurisdictional ambiguity, anti-money laundering (AML) and Know-Your-Customer (KYC) compliance, investor protection, and financial stability. Applications like Uniswap, Aave as well as MakerDAO example opportunities and threats. The same problem has dominated the United States, European Union and the emerging economies, as has been described in the comparison analysis of the response in regulation; tension of stimulation of innovation and protection of the financial structure. Research indicates that although DeFi has a revolutionary potential in relation to open finance, its decentralized form makes it difficult to regulate. It needs to be a middle ground between international coordination, hybrid sandboxes and technology neutral policy to not just promote resilience and consumer protection, but also creativity.
Recent years have seen many industrial implementations and much scholastic research, i.e., prototypes and theoretical frameworks, in Decentralized Identity Management Systems (DIDMS). It is safe to say that Attestation-Based Attribute-Based Decentralized IDM (ABABDIDM) has not received anywhere near the same level of attention in the literature as general Attribute-Based DIDMs (ABDIDM), i.e, decentralized Attribute-Based Access Control (ABAC). The use of decentralization, i.e., DIDM, is to improve upon the security and privacy-related issues of centralized Identity Management Systems (IDM) and Attribute-Based IDMs (ABIDM). And blockchain is the framework used for decentralization in all these schemes. Many DIDMs - even ABDIDMs - have been defined on popular blockchains such as Hyperledger, Ethereum, and Bitcoin. However, despite the characteristics of Ripple that makes it appealing for an ABIDM, there is a lack of research to develop an Identity Management System (IDMS) on Ripple in literature. We have attempted to conceptualize an ABABDIDM on Ripple.
As datasets become critical assets in modern machine learning systems, ensuring robust copyright protection has emerged as an urgent challenge. Traditional legal mechanisms often fail to address the technical complexities of digital data replication and unauthorized use, particularly in opaque or decentralized environments. This survey provides a comprehensive review of technical approaches for dataset copyright protection, systematically categorizing them into three main classes: non-intrusive methods, which detect unauthorized use without modifying data; minimally-intrusive methods, which embed lightweight, reversible changes to enable ownership verification; and maximally-intrusive methods, which apply aggressive data alterations, such as reversible adversarial examples, to enforce usage restrictions. We synthesize key techniques, analyze their strengths and limitations, and highlight open research challenges. This work offers an organized perspective on the current landscape and suggests future directions for developing unified, scalable, and ethically sound solutions to protect datasets in increasingly complex machine learning ecosystems.
Modern vehicles accumulate fragmented lifecycle records across OEMs, owners, and service centers that are difficult to verify and prone to fraud. We propose VehiclePassport, a GAIA-X-aligned digital passport anchored on blockchain with zero-knowledge proofs (ZKPs) for privacy-preserving verification. VehiclePassport immutably commits to manufacturing, telemetry, and service events while enabling selective disclosure via short-lived JWTs and Groth16 proofs. Our open-source reference stack anchors hashes on Polygon zkEVM at <$0.02 per event, validates proofs in <10 ms, and scales to millions of vehicles. This architecture eliminates paper-based KYC, ensures GDPR-compliant traceability, and establishes a trustless foundation for insurance, resale, and regulatory applications in global mobility data markets.
In this paper, we design, implement, and empirically evaluate a tamper-evident, blockchain-secured solar energy logging system for resource-constrained edge Internet of Things (IoT) devices. Using a Merkle tree batching approach in conjunction with threshold-triggered blockchain anchoring, the system combines high-frequency local logging with energy-efficient, cryptographically verifiable submissions to the Ethereum Sepolia testnet, a public Proof-of-Stake (PoS) blockchain. The logger captured and hashed cryptographic chains on a minute-by-minute basis during a continuous 135 h deployment on a Raspberry Pi equipped with an INA219 sensor. Thanks to effective retrial and daily rollover mechanisms, it committed 130 verified Merkle batches to the blockchain without any data loss or unverifiable records, even during internet outages. The system offers robust end-to-end auditability and tamper resistance with low operational and carbon overhead, which was tested with comparative benchmarking against other blockchain logging models and conventional local and cloud-based loggers. The findings illustrate the technical and sustainability feasibility of digital audit trails based on blockchain technology for distributed solar energy systems. These audit trails facilitate scalable environmental, social, and governance (ESG) reporting, automated renewable energy certification, and transparent carbon accounting.
Arash Peik, Mohammad Ali Zare Chahooki, Amin Milani Fard, Mehdi Agha Sarram
Precise short-term price prediction in the highly volatile cryptocurrency market is critical for informed trading strategies. Although Temporal Fusion Transformers (TFTs) have shown potential, their direct use often struggles in the face of the market's non-stationary nature and extreme volatility. This paper introduces an adaptive TFT modeling approach leveraging dynamic subseries lengths and pattern-based categorization to enhance short-term forecasting. We propose a novel segmentation method where subseries end at relative maxima, identified when the price increase from the preceding minimum surpasses a threshold, thus capturing significant upward movements, which act as key markers for the end of a growth phase, while potentially filtering the noise. Crucially, the fixed-length pattern ending each subseries determines the category assigned to the subsequent variable-length subseries, grouping typical market responses that follow similar preceding conditions. A distinct TFT model trained for each category is specialized in predicting the evolution of these subsequent subseries based on their initial steps after the preceding peak. Experimental results on ETH-USDT 10-minute data over a two-month test period demonstrate that our adaptive approach significantly outperforms baseline fixed-length TFT and LSTM models in prediction accuracy and simulated trading profitability. Our combination of adaptive segmentation and pattern-conditioned forecasting enables more robust and responsive cryptocurrency price prediction.
We introduce a novel rough Bergomi (rBergomi) model featuring a variance-driven exponentially weighted moving average (EWMA) time-dependent Hurst parameter $H_t$, fundamentally distinct from recent machine learning and wavelet-based approaches in the literature. Our framework pioneers a unified rough differential equation (RDE) formulation grounded in rough path theory, where the Hurst parameter dynamically adapts to evolving volatility regimes through a continuous EWMA mechanism tied to instantaneous variance. Unlike discrete model-switching or computationally intensive forecasting methods, our approach provides mathematical tractability while capturing volatility clustering and roughness bursts. We rigorously establish existence and uniqueness of solutions via rough path theory and derive martingale properties. Empirical validation on diverse asset classes including equities, cryptocurrencies, and commodities demonstrates superior performance in capturing dynamics and out-of-sample pricing accuracy. Our results show significant improvements over traditional constant-Hurst models.
Traditional security models for Nakamoto-style blockchains assume instantaneous synchronization among malicious nodes, which overestimate adversarial coordination capability. We revisit these existing models and propose two more realistic security models. First, we propose the static delay model. This model first incorporates adversarial communication delay. It quantifies how the delay constrains the effective growth rate of private chains and yields a closed-form expression for the security threshold. Second, we propose the dynamic delay model that further captures the decay of adversarial corruption capability and the total adversarial delay window. Theoretical analysis shows that private attacks remain optimal under both models. Finally, we prove that large-scale Nakamoto-style blockchains offer better security. This result provided a theoretical foundation for optimizing consensus protocols and assessing the robustness of large-scale blockchains.
Ali M. Emran, Md Kamrul Islam -, Md Ashraful Islam Nayem -, Md Rubel · 5 authors
Abstract: Exploring GNNs as a cutting-edge approach to real-time detection of online money transfer fraud is the focus of this work. P2P payment systems, mobile money platforms, and decentralized financial infrastructures (DeFi) have all experienced explosive growth over the past decade due to their simplicity, speed, and affordability. Identity fraud, synthetic account misuse, coordinated fraud rings that exploit systemic vulnerabilities, and transaction laundering are some of the new types of fraud that can occur in these platforms, despite their desirability. In situations where fraud is predictable, isolated, and statistically distinct, logistic regression, rule-based algorithms, and standard ML models like Random Forests and SVMs have all proved effective in detecting it. Modern, hyper-connected, real-time financial ecosystems are seeing an uptick in non-linear, relational, and temporal fraud patterns, which these tactics struggle to combat. Because of their inherent bias, they fail to recognize the interconnected structural and relational processes that may point to coordinated fraud. The graph-like qualities of monetary exchanges, where elements (like IP addresses, users, and devices) are organically linked through edges that stand for transactions or relationships, are utilized by Graph Neural Networks to give a paradigm shift, on the other hand. Generalized neural networks (GNNs) are crucial for uncovering intricate fraud schemes because they represent these interactions as a graph structure that permits data to travel and accumulate across nodes. Because of this, the model may take global and regional effects into consideration. Relational learning excels when other methods fail, such as when trying to detect suspicious clusters of transactions, multi-hop collusions, or fraudulent subnetworks using separate features. In order to implement this method, we constructed an entirely new fraud detection system utilizing GNNs. Node feature engineering, graph generation, classification heads, message-passing layers, and a real-time processing optimized pipeline are all parts of it. We were able to empirically evaluate our technique using a real-world transactional dataset that was acquired from a leading financial services provider. As is typical in fraud detection tasks, the dataset had a highly skewed class distribution, which impacted both memory and accuracy. With an F1-score of 0.78, accuracy of 98.7 percent, precision of 0.81%, and recall of 0.76%, the model nevertheless performed admirably. The model's ability to detect fraudulent behaviors while maintaining dependable operations in the real world is demonstrated by these measures. Beyond its implications for technological performance, this study will help achieve broader aims in regulation, ethics, and national security. A number of federal agencies have issued advisories highlighting the need for strong, intelligent, and real-time fraud monitoring systems to safeguard national financial systems from fraudulent exploitation. These agencies include the DOJ, FinCEN, and DHS. Compliance with the USA PATRIOT Act and the Bank Secrecy Act (BSA) is of the utmost importance to financial institutions and fintech enterprises. As stated in the National Strategy to Combat Terrorist and Other Illicit Financing, they also want AI-driven surveillance systems to be resilient and explainable. This national goal is helped by our study, which provides a scalable, interpretable, and performance-driven GNN-based system. Along with helping with auditability, model explainability, and compliance reporting, all of which are crucial for regulated businesses, this strategy also helps with effective fraud detection. Integrating our suggested architecture for decentralized, privacy-preserving fraud detection into online learning extensions can further improve their functionality. Over time, these extensions can be integrated with federated learning systems and streaming data platforms. This work puts GNNs in a position to become a new weapon in the fight against digital payment fraud by combining cutting-edge graph representation learning with cybersecurity regulations and goals for financial integrity. Thanks to our research's careful analysis, innovative architecture, and adherence to statutory criteria, future financial systems will be reliable, safe, and robust. Additionally, it resolves a significant technical matter.
The convergence of artificial intelligence (AI), multi-access edge computing (MEC), and cloud environments has transformed identity governance by enabling real-time decision-making and seamless access control across decentralized infrastructures. However, this evolution has also introduced complex challenges concerning data privacy, identity trust, and security. This review explores privacy-first security models that integrate AI for identity governance in hybrid cloud-edge architectures. It evaluates privacy-preserving techniques such as homomorphic encryption, federated learning, and zero-knowledge proofs, emphasizing their role in ensuring secure identity authentication, authorization, and auditability. The paper critically analyzes the limitations of conventional identity and access management (IAM) frameworks in dynamic, resource-constrained edge environments and proposes adaptive models that embed privacy by design. Furthermore, the review investigates the interplay between explainable AI (XAI) and policy enforcement for transparent and compliant identity governance. By synthesizing advancements in cryptographic methods, AI reasoning engines, and decentralized identity (DID) systems, the paper outlines a roadmap for building secure, scalable, and privacy-compliant identity infrastructures in the era of pervasive computing. Keywords: Privacy-Preserving Identity Governance, AI-Driven Access Control, Multi-Access Edge Computing (MEC). Federated Identity Management, Explainable AI (XAI), Zero-Knowledge Proofs.
Decentralized Finance (DeFi) attacks have resulted in significant losses, often orchestrated through Adversarial Exploiter Contracts (AECs) that exploit vulnerabilities in victim smart contracts. To proactively identify such threats, this paper targets the explainable detection of AECs. Existing detection methods struggle to capture semantic dependencies and lack interpretability, limiting their effectiveness and leaving critical knowledge gaps in AEC analysis. To address these challenges, we introduce SEASONED, an effective, self-explanatory, and robust framework for AEC detection. SEASONED extracts semantic information from contract bytecode to construct a semantic relation graph (SRG), and employs a self-counterfactual explainable detector (SCFED) to classify SRGs and generate explanations that highlight the core attack logic. SCFED further enhances robustness, generalizability, and data efficiency by extracting representative information from these explanations. Both theoretical analysis and experimental results demonstrate the effectiveness of SEASONED, which showcases outstanding detection performance, robustness, generalizability, and data efficiency learning ability. To support further research, we also release a new dataset of 359 AECs.
Time series forecasting plays a critical role in decision-making processes across diverse fields including meteorology, traffic, electricity, economics, finance, and so on. Especially, predicting returns on financial instruments is a challenging problem. Some researchers have proposed time series foundation models applicable to various forecasting tasks. Simultaneously, based on the recognition that real-world time series exhibit chaotic properties, methods have been developed to artificially generate synthetic chaotic time series, construct diverse datasets and train models. In this study, we propose a methodology for modeling financial time series by generating artificial chaotic time series and applying resampling techniques to simulate financial time series data, which we then use as training samples. Increasing the resampling interval to extend predictive horizons, we conducted large-scale pre-training using 10 billion training samples for each case. We subsequently created test datasets for multiple timeframes using actual Bitcoin trade data and performed zero-shot prediction without re-training the pre-trained model. The results of evaluating the profitability of a simple trading strategy based on these predictions demonstrated significant performance improvements over autocorrelation models. During the large-scale pre-training process, we observed a scaling law-like phenomenon that we can achieve predictive performance at a certain level with extended predictive horizons for chaotic time series by increasing the number of training samples exponentially. If this scaling law proves robust and holds true across various chaotic models, it suggests the potential to predict near-future events by investing substantial computational resources. Future research should focus on further large-scale training and verifying the applicability of this scaling law to diverse chaotic models.
Andrei Damian, Petrica Butusina, Alessandro De Franceschi, Vitalii Toderian · 6 authors
We propose the Ratio1 AI meta-operating system (meta-OS), a decentralized MLOps protocol that unifies AI model development, deployment, and inference across heterogeneous edge devices. Its key innovation is an integrated blockchain-based framework that transforms idle computing resources (laptops, smartphones, cloud VMs) into a trustless global supercomputer. The architecture includes novel components: a decentralized authentication layer (dAuth), an in-memory state database (CSTORE), a distributed storage system (R1FS), homomorphic encrypted federated learning (EDIL), decentralized container orchestration (Deeploy) and an oracle network (OracleSync), which collectively ensure secure, resilient execution of AI pipelines and other container based apps at scale. The protocol enforces a formal circular token-economic model combining Proof-of-Availability (PoA) and Proof-of-AI (PoAI) consensus. Compared to centralized heterogeneous cloud MLOps and existing decentralized compute platforms, which often lack integrated AI toolchains or trusted Ratio1 node operators (R1OP) mechanics, Ratio1's holistic design lowers barriers for AI deployment and improves cost-efficiency. We provide mathematical formulations of its secure licensing and reward protocols, and include descriptive information for the system architecture and protocol flow. We argue that our proposed fully functional ecosystem proposes and demonstrates significant improvements in accessibility, scalability, and security over existing alternatives.
Although the P2P power transactions using the multiagent deep deterministic policy gradient (MADDPG) algorithm has been extensively studied, there are still challenges in privacy protection and training incentives. Furthermore, the stability and efficiency of the strategy decreases when dealing with nonindependent identically distribution (Non-IID) data from heterogeneous prosumers. Therefore, this article proposes a blockchain-enabled asynchronous federated learning-MADDPG (BEAFL-MADDPG) framework designed to enhance the training efficiency of heterogeneous prosumers while safeguarding data privacy. The framework includes a novel P2P energy trading model that facilitates energy trading amidst incomplete information while ensuring privacy assurances. In addition, a BEAFL-MADDPG algorithm is proposed, which accelerates training processes and enables parallel computation among agents. This algorithm enhances the efficiency of algorithm and empowers the training of diverse prosumers. Furthermore, a blockchain-enabled training mechanism and prosumer incentive scheme are proposed that not only encourage prosumer engagement in training but also ensure traceable transactions without the need for trust among participants. These mechanisms promote transparency and integrity, fostering a collaborative and secure environment for energy trading. Simulation results demonstrate that the framework achieves peak load reduction through optimized P2P trading, maintains computation efficiency across discount rates, and ensures secure transactions via blockchain-based incentives. These practical benefits support scalable and sustainable community microgrid operations.