Along with the sustained occurrence of black swan events in the decentralized application ecosystem, smart contract security is a growing concern. Traditional solutions mainly rely on predefined rules, while highly accurate, require intensive manual code analysis. Machine learning methods (mainly based on BERT) leverage semantic and contextual information, but overlook crucial code structure features, which are critical for identifying vulnerability. Furthermore, the presence of useless or harmful attention heads in the BERT model leads to less robust predictions and slows down processing speeds. We propose a novel method named Pruning attention Heads based on Semantic and Code Structure (PHSCS) for Smart Contract Vulnerability Detection. Specifically, we introduce a new structure-aware pre-training programming language task, Variable Edge Prediction, which bypasses the use of data flow nodes as input and directly predicts data flow edges between variables, aiming to efficiently learn code structure while ensuring the ability to process extensive code. Additionally, we present a pruning strategy to optimize BERT, tailored to the semantic and structural peculiarities of code. By employing Taylor Expansion for evaluating attention heads' significance and guiding their pruning, iteratively refined the BERT model. Experiment results on 8 vulnerability types illustrate that the PHSCS method surpasses state-of-the-art methods.
This paper provides a comprehensive analysis of the evolving security risks and regulatory compliance challenges facing Bitcoin in financial applications. While Bitcoin's cryptographic foundations and decentralized architecture offer strong protections, emerging threatsâsuch as consensus attacks, network exploits, privacy leaks, and operational vulnerabilitiesâpose significant risks to financial institutions. Simultaneously, global regulatory frameworks are tightening, particularly around AML, KYC, and consumer protection, compelling institutions to implement robust compliance strategies. The study synthesizes insights from computer science, finance, and law to propose integrated approaches combining technical safeguards with regulatory adherence. Strategies such as multi-signature controls, blockchain analytics, secure custody solutions, and âcompliance by designâ are explored. The paper concludes by discussing future risks including quantum computing and privacy-compliance tensions, emphasizing the need for adaptive risk management in institutional Bitcoin adoption.
Recep Arslan, Mustafa Ăzseven, Metin Mutlu Aydın
European cybersecurity is rapidly evolving to address complex and emerging threats fueled by advancements in technology. AI-powered threat analysis has become a cornerstone, enabling faster detection of anomalies, predictive threat modeling, and real-time incident response. As Europe enters the quantum age, cybersecurity strategies are increasingly focused on quantum-resistant encryption to protect critical infrastructure and sensitive data from future quantum attacks. Simultaneously, the rise of blockchain technologies and cryptocurrencies introduces new vulnerabilities, such as smart contract exploits and decentralized finance (DeFi) fraud, requiring targeted regulatory oversight. In response, the EU is strengthening its regulatory frameworks, such as the NIS2 Directive and the Digital Operational Resilience Act (DORA), to ensure a harmonized, proactive approach to cybersecurity governance, resilience, and accountability across sectors. This multifaceted strategy reflects Europeâs commitment to safeguarding digital sovereignty and fostering trust in its digital ecosystem. The study deals with the transformation of the European cyber security ecosystem within the framework of artificial intelligence (AI) supported threat analysis. The paper discusses the security risks that arise in the quantum and post-quantum era, the possibility of blockchain/crypto systems being broken by quantum computers, the limitations of the existing data set, and the need for human-like thinking skills. In addition, the European Union's (EU) cybersecurity policies, data privacy principles, ethical standards, transparency, accountability, and human-centered AI design approaches are examined within the scope of the EU's global norm-setting role. This article also aims to shed light on the strategic steps that will shape the future of AI-powered cyber defense. Study shows that Europe should develop artificial intelligence (AI)-powered cybersecurity solutions in its preparations for the post-quantum era, it also should invest in AI models that transcend current data set limits and have humanoid thinking capacities.
Smart contracts have revolutionized the way transactions are executed, offering decentralized and immutable frameworks. The immutability of smart contracts poses significant risks when vulnerabilities exist in their code, leading to financial losses. Despite advancements in using deep learning for smart contract vulnerability detection (SCVD), existing methods struggle with the complex logic and intricate semantics embedded within smart contract code. Large Language Models (LLMs) have shown promise in providing deeper insights into smart contract logic. However, LLMs, such as GPT follow a decoder-only architecture and are trained in an unsupervised manner rather than learning specific labels. In the SCVD task, these LLMs have difficulty in capturing information related to vulnerabilities, leading to very low accuracy. Therefore, we propose CodeXplain, a novel SCVD approach that leverages the deep insights into code from LLM and the supervised learning capabilities of deep learning models to set the latest advance and performance. In particular, we deeply analyze 14 types of dangerous and common smart contract vulnerabilities. Based on the rationale of these vulnerabilities, nine perspective prompts are introduced to guide LLMs in generating code explanations that contribute to SCVD. Then, we propose a CodeT5-based semantic fusion module integrating smart contract code and code explanations. Finally, the performance of SCVD is improved by performing supervised learning on trusted labels. Experimental results on 3,544 real-world smart contracts demonstrate that CodeXplain outperforms 16 state-of-the-art SCVD methods, achieving an F1-score of 94.12% and an accuracy of 93.88%, surpassing all baselines.
Ioannis Sfyrakis, Paolo Modesti, Lewis Golightly, Minaro Ikegima
Blockchain and smart contracts have transformed industries by automating complex processes and transactions. However, this innovation has introduced significant security concerns, potentially leading to loss of financial assets and data integrity. The focus of this research is to address these challenges by developing a tool that can enable developers and testers to detect vulnerabilities in smart contracts in an efficient and reliable way. The research contributions include an analysis of existing literature on smart contract security, along with the design and implementation of a lightweight vulnerability detection tool called LightCross. This tool runs two well-known detectors, Slither and Mythril, to analyse smart contracts. Experimental analysis was conducted using the SmartBugs curated dataset, which contains 143 vulnerable smart contracts with a total of 206 vulnerabilities. The results showed that LightCross achieves the same detection rate as SmartBugs when using the same backend detectors (Slither and Mythril) while eliminating SmartBugsâ need for a separate Docker container for each detector. Mythril detects 53% and Slither 48% of the vulnerabilities in the SmartBugs curated dataset. Furthermore, an assessment of the execution time across various vulnerability categories revealed that LightCross performs comparably to SmartBugs when using the Mythril detector, while LightCross is significantly faster when using the Slither detector. Finally, to enhance user-friendliness and relevance, LightCross presents the verification results based on OpenSCV, a state-of-the-art academic classification of smart contract vulnerabilities, aligned with the industry-standard CWE and offering improvements over the unmaintained SWC taxonomy.
Abdullah Mubarak Al Dhaheri, Mohammad Amin Alkrisheh, Tayil Mahmoud Shiyab, Ibrahim Al Nuaimi
This research addresses the issue of the illicit use of digital cryptocurrencies, considering it one of the most pressing contemporary legal challenges facing legislative systems, particularly given the unique technical features of these currencies-such as encryption, decentralisation, and anonymity. The significance of the study lies in examining the legal impact of cryptocurrencies on cybersecurity and analysing the adequacy of the legal framework in the United Arab Emirates in confronting crimes arising from their use. The study's core problem lies in the absence of a comprehensive legislative framework that regulates the use of cryptocurrencies and limits their exploitation in cross-border crimes, such as money laundering and terrorist financing. It also lies in the technical difficulties of tracking digital transactions and the lack of well-established legal concepts regarding the possession of cryptocurrencies and the liability of those dealing with them. The research adopts an analytical methodology through the study of relevant legal texts, in particular, Federal Decree-Law No. 20 of 2018 on Anti-Money Laundering and Combating the Financing of Terrorism and Illegal Organisations; Federal Law No. 34 of 2021 on Combating Rumours and Cybercrimes; and Law No.4 of 2022 on the Regulation of Virtual Assets in the Emirate of Dubai. The study concludes that the current legislative structure is advanced at the regional level but requires further specialisation and technical flexibility. The study recommends issuing a federal law addressing digital assets, enhancing international cooperation in information exchange, adopting technical solutions such as artificial intelligence to track digital crimes, and equipping the competent authorities with advanced legal tools to regulate transactions in this field.
A segurança de contratos inteligentes continua sendo um desafio na blockchain Ethereum. Este artigo investiga a evolução de ferramentas de anĂĄlise de segurança por meio de dois experimentos com a estrutura SmartBugs. O primeiro analisa 215 contratos do Etherscan verificados recentemente, focando nas vulnerabilidades detectadas. O segundo replica um estudo de 2020, usando o mesmo conjunto de contratos com vulnerabilidades, mas com ferramentas atualizadas. Resultados indicam defasagem da taxonomia DASP Top 10 e uma queda na precisĂŁo de detecção (de 41,7% para 24,3%), levantando dĂșvidas sobre o real progresso das ferramentas.
The success of terrorist organizations in maintaining traditional resources to finance terrorist operations is sufficient to push them away from virtual currencies and their usual risks, as long as they are able to sell oil and transfer funds between their territories, and as long as their funds remain safe from attacks and persecution by the international community. Encrypted virtual currencies are characterized by high degrees of secrecy, privacy, and decentralization - and extremist religious groups And terrorism that adopts violence as a means of operation and expansion, and studying indicators indicating the growing importance of these currencies in circulation, exchange, and commercial transactions, nd in financing extremist religious groups and organizations, and financing the purchase of weapons and equipment used by these groups. It is a decentralized currency with no competent authority, and no central bank responsible for issuing it, and it is not subject to the restrictions of international banking and monetary institutions. This is a significant advantage that has attracted many individuals and groups to its circulation. Had international institutions and organizations been able to subject this currency to international oversight, or to a central authority, it would have lost its most important advantage, and terrorist and extremist organizations would have been unable to exploit it further.
This paper analyzes the risks posed by future-state quantum computers, specifically the âharvest now decrypt laterâ (HNDL) risk. We review foundational concepts of quantum computing to address the present and ongoing threat of HNDL to currently protected data. We use the Bitcoin network as an illustrative example to study the implications of HNDL for distributed ledger cryptocurrency networks that rely upon traditional cryptography. We posit that while cryptocurrency distributed ledger network maintainers could successfully deploy post-quantum cryptography (PQC) mitigations to protect the networkâs security and data integrity against a future-state quantum computer, data privacy of the networkâs previously recorded transactions remains vulnerable against a future-state quantum computer due to HNDL. The difficulty in protecting data privacy lies in the risk that a bad actor can obtain a distributed ledger replica, harvest the data, and in the fullness of time reveal previously obfuscated and confidential data using a sufficiently powerful quantum computer. The authors highlight this gap in data privacy protection and note the shortage of mitigations for the data privacy risks associated with the HNDL threat within distributed ledger networks.
Maria Dona Kristina Wati, Ainul Azizah, Fanny Tanuwijaya
The rapid development of digital technology has transformed the global financial landscape with the emergence of virtual currencies such as Bitcoin. As a decentralized digital asset based on blockchain technology, Bitcoin enables fast, anonymous, and cross-border transactions without central authority intervention. While these features offer convenience, they also pose risks of abuse in illegal activities, including narcotics transactions. In Indonesia, the use of Bitcoin in drug-related offenses presents complex legal challenges due to the absence of explicit criminal regulations governing such usage. This study examines the criminal liability of narcotics offenders who utilize Bitcoin, focusing on three core issues: the juridical basis for punishment, the characteristics of punishment under Indonesiaâs legal system, and an ideal penal concept for the future. The research employs a normative juridical method with statutory, conceptual, and case study approaches. Findings indicate that punishment remains based on Law No. 35 of 2009 on Narcotics, with Bitcoin regarded as a means rather than a core element of the crime. Although it does not constitute a new offense, its use may aggravate punishment through individualized sentencing. Sanctions involving digital assets remain suboptimal due to regulatory gaps. Therefore, this study recommends revising criminal laws to explicitly regulate Bitcoin use in drug crimes, developing sentencing guidelines that consider technological factors, and formulating responsive penal policies, including asset seizure and inter-agency collaboration through blockchain forensic technology.
Decentralized Finance (DeFi) represents the new generation of blockchain financial services by developing an open-access financial model without banking or lending institution intermediaries. However, DeFi's open feature threatens its security, making it vulnerable and a target for different attack types. In this systematic review, we present the security of DeFi by selecting fifteen studies from 2020 to 2024 to determine and display the security solutions' effectiveness in identifying the attacks, focusing on various DeFi components such as smart contracts, DEX, AMM, governance, AMM-based DEX, and smart contracts with (DEX, Oracle); detecting different kinds of attacks (e.g., price manipulation, Oracle manipulation, flash loan) using detection tools (e.g., DeFort, CRPWarner, FORAY); we find out that 40% of the selected studies focus on Oracle manipulation attack, 33.33% for price manipulation and flash loan attacks separately, followed by 13.33% for (MEV, rug pull, front-running, Token Leakage, and deep logical bugs), 6.67% for (EEV, reentrancy, sandwich, access control, and state derailment defects). We compare the studies based on the attack type that they detected using four state-of-the-art types of research, such as DeFiScope, FlashSyn, SecPLF, and DeFiGuard; this indicates the concentration of the trend studies is on accuracy and combining AI in DeFi security, or aggregating the existing tools with it, giving an overview of DeFi components' security, underlining the gaps in the attack types that future research can address to build more robust, trustworthy, and secure DeFi systems.
This article examines how the design features of retail central bank digital currencies (CBDCs) influence the detection and prevention of crypto-enabled money laundering. Drawing on a comparative analysis of Russia, the European Union, the United States, and Malta, it evaluates the effectiveness of CBDC-integrated anti-money laundering (AML) mechanisms in addressing the three key stages of illicit finance: placement, layering, and integration. Using primary sources, including pilot program data, legislative texts, and policy consultations, alongside secondary academic literature, the Study explores how design elements such as ledger visibility, programmable transaction limits, sanctions screening, and tiered privacy structures can be embedded into CBDC infrastructure. The findings reveal significant variation in enforcement capacity, privacy protection, and governance transparency across jurisdictions, shaped by political economy, legal traditions, and technological architectures. The article argues that while CBDCs offer unprecedented opportunities to embed compliance at the core of payment systems, their legitimacy and adoption depend on the careful balancing of enforcement effectiveness with constitutional safeguards, civil liberties, and public trust. Policy recommendations emphasize jurisdiction-specific typology mapping, programmable safeguards, stakeholder engagement, tiered anonymity, cross-border interoperability, and independent oversight. The analysis concludes that CBDCs, if responsibly designed, can modernize AML frameworks and strengthen financial integrity without undermining democratic principles.
Nguyen Dang Quynh Nhu, Quan Li, Thai Hung Van, Doan Minh Trung · 5 authors
The burgeoning adoption of economically incentivized smart contracts faces persistent security vulnerabilities, resulting in significant financial losses due to their immutability post-deployment. This paper presents a novel framework integrating fine-tuned large language models (LLMs) with Retrieval-Augmented Generation (RAG) to enhance the precision and explainability of smart contract vulnerability detection. By fine-tuning an open-source LLM and employing RAG, our model dynamically incorporates domain-specific external knowledge during inference, significantly improving threat identification. On two public benchmarks, SolidiFI-Benchmark and Smart Bugs Curated, our fine-tuned Qwen2.5-Coder-14B model (QC-14B-FT) outperforms zero-shot LLMs (GPT-3.5 with and without RAG) in terms of F1-score. Specifically, QC-14B-FT achieves an F1-score of 0.64 on SolidiFI, surpassing GPT-3.5-RAG by 9% and GPT-3.5 by 10%. On Smart Bugs Curated, QC-14B-FT achieves an F1-score of 0.73, outperforming GPT-3.5-RAG by 14% and GPT-3.5 by 19%. These results demonstrate the effectiveness of combining RAG with fine-tuning to provide accurate and clear smart contract security assessments.
Ruba Islayem, Senay A. Gebreab, Walaa AlKhader, Ahmad Musamih · 7 authors
Traditional health insurance claim processing systems are plagued by inefficiencies and vulnerabilities, often resulting in significant financial losses due to fraudulent activities. Existing fraud detection methods are largely manual, time-consuming, and inadequate for handling the complexity and scale of modern fraudulent schemes. Moreover, the trust-based relationships between insurers and healthcare providers lack mechanisms to ensure data integrity and prevent manipulation. While several blockchain-based systems have been proposed to improve transparency and tamper resistance, they typically focus on structured data and predefined fraud types, offering limited adaptability and analytical insight. This paper proposes a novel solution leveraging blockchain technology and Large Language Models (LLMs) to transform fraud detection. The system uses Ethereum smart contracts (SCs) to securely store medical records and claim details on a decentralized, tamper-proof ledger that ensures data integrity, traceability, and accountability. This immutable data is accessed by an LLM via a Retrieval-Augmented Generation (RAG) system, which enables intelligent retrieval and analysis of relevant clinical information to detect fraud patterns and inconsistencies. To support complex scenarios involving free-text documents, unstructured clinical data, such as lab reports, are stored using decentralized off-chain storage and retrieved during LLM analysis. In addition, an LLM-powered chatbot also allows insurance providers to interact with the system in natural language for claim inquiries, explanations, and summaries. The architecture, sequence diagrams, and implementation algorithms outline the development process, while testing scenarios demonstrate the system's ability to detect fraud such as inflated costs, unnecessary treatments, and unrendered services. Evaluation using both synthetic and public clinical datasets showed strong performance, with the LLM achieving up to 99% fraud detection accuracy. Cost, security, and scalability analyses confirm the system's practicality and resilience, with the complete detection process executing in just 13 seconds. By overcoming the limitations of traditional systems, this framework offers a scalable and adaptable approach for healthcare and other domains. The SCs and source code are publicly available on GitHub.
Yonso Alain Bertrand, Abeye Michel Patrice Davy, Ndassimba Edgard, Ouya Samuel
On February 10, 2025, the Central African Republic launched a cryptocurrency named "CAR." Initiated by the Ministry of Mines and Geology, the project was carried out by the Minerals and Gems Exchange in collaboration with Barnley. Despite this technological leap, the management of natural resources continues to encounter critical issues, including fraud, corruption, and insufficient transparency in transactions. The lack of an effective traceability system limits governmental oversight and enables illicit flows. This paper proposes a blockchain-based solution built on the Ethereum platform to enhance the security and transparency of operations involving natural resources. The implementation makes use of Ganache for blockchain simulation, Solidity for smart contract development, and Express.js for backend infrastructure. A REST API facilitates interaction with the blockchain, ensuring a tamper-proof record of transactions. The methodological approach follows a decentralized architecture in which smart contracts automate the recording and validation of operations. A series of tests assessed both the technical feasibility and the performance of the system. Findings reveal that blockchain integration significantly improves transparency, minimizes the risk of falsification, and supports efficient transaction verification. The immutable nature of the data strengthens trust among stakeholders and contributes to more effective sector regulation. This technological strategy marks a meaningful step toward curbing fraudulent activities and optimizing natural resource governance. It also establishes a dependable and durable framework, offering a valuable tool for policymakers and investors dedicated to ethical resource exploitation in the Central African Republic.
In an era marked by increasingly sophisticated cyber threats and growing vulnerabilities in national critical infrastructure, this study explores the transformative role of confidential computing in defending against emerging cryptographic attacks and enabling secure threat intelligence sharing. Traditional cybersecurity measures, while effective for protecting data at rest and in transit, fall short in securing data during active processingan area exploited by advanced persistent threats, quantum computing, and side-channel attacks. This research investigates how hardware-based trusted execution environments (TEEs), homomorphic encryption, and zero-knowledge proofs embedded in confidential-computing platforms can preserve the confidentiality of sensitive operations even within potentially compromised environments. Through detailed case studies of major U.S. institutionsincluding PGandE, Exelon, JPMorgan Chase, Wells Fargo, and Kaiser Permanentethe paper demonstrates significant improvements in detection speed, false positive reduction, and operational efficiency. Furthermore, it proposes a scalable, privacy-preserving framework for collaborative cyber defense across critical sectors such as energy, finance, and healthcare. The findings underscore that integrating confidential computing with decentralized intelligence sharing networks not only enhances cybersecurity resilience but also yields substantial economic and regulatory benefits. This work advocates for a national, and eventually global, shift toward confidential-computing-enabled infrastructures to achieve robust, cooperative, and future-proof cyber defense ecosystems.
Ramazan BektaĆ, Kerim Eser AFĆAR, Ahmet Aydın Arı
Cryptocurrencies initially gained prominence by eliminating intermediaries in payment systems and later found applications in various business sectors. The crypto network, pioneered by Bitcoin, has spurred new business forms and organizational structures with diverse motivations. Bitcoin's emergence is technically dated to 2008. However, its ideological and technical roots trace back to the cyberpunk literature of the late 1970s and the cypherpunk movement that began in California in 1992. The cypherpunk manifestos significantly influenced cryptographic work, shaping Bitcoin's technical foundation. This study aims to explore Bitcoin's ideological origins through a qualitative content analysis of cypherpunk manifestos, Nakamoto's posts on the "Bitcointalk" forum, and "Cryptography Mailing List" correspondence. By examining these sources, the study identifies the historical dimensions of Bitcoin's technical structure and highlights the impact of ideological debates on its development. Findings reveal that while cryptographic research influenced Bitcoin's technical evolution, ideological discussions were relatively less significant. Nonetheless, Bitcoin's developers, particularly Nakamoto, incorporated a strong ideological emphasis on "privacy" despite the primary technical focus.
Abstract The advent of blockchain technology has achieved notable progress regarding security, particularly within the realm of e-commerce. The existing Web 2.0 framework, which employs inadequate security measures, exhibits vulnerabilities when compared to the robust security features of blockchain technology. The utilization of monitors, computers, and data storage exemplifies the functionality of blockchain technology, which upholds encrypted and distributed transaction records across multiple computers, consequently improving the reliability of the digital ledger. In a nation such as Bangladesh, where transaction data is susceptible to cyber threats and online fraud is prevalent within the e-commerce sector, this type of decentralized system has the potential to alter the landscape significantly. This requires the implementation of a more comprehensive security protocol. This research advocates for the adoption of smart contracts to enhance supply chain transparency and offers digital identification solutions aimed at preventing fraud, including issues related to non-delivery and counterfeit goods. This research utilizes Next.js for front-end development and facilitates backend integration through Solidity and Hardhat.js, specifically for the Solana Blockchain, deployed on an Amazon EC2 instance. This research commenced with an examination of the current e-commerce ecosystem, physical identification infrastructure, and consumer attitudes, ultimately presenting a strategic implementation plan for the adoption of blockchain technology to enhance trust and assurance within the e-commerce landscape of Bangladesh. It further delineates particular obstacles to adoption: technological limitations, regulatory challenges, socio-economic factors, and the expanding digital payments landscape, particularly concerning mobile financial services. This research enhances the current understanding of blockchain as a transformative force in emerging e-commerce markets and provides valuable insights into technology policies relevant to the developing economy of Bangladesh for policymakers, businesses, and technologists. Graphical abstract
ABSTRACT Smart Contracts ensure trust through blockchain technology, streamline processes, and have disruptive potential across various industries. However, the issue of smart contract security cannot be underestimated. The vulnerability of smart contracts to exploitation has led to substantial losses, prompting increased attention toward vulnerability mining. Existing efforts for analyzing contract security heavily depend on inflexible rules set by experts, making them nonâadaptable or scalable. Although various machineâlearning methods have emerged for vulnerability mining in smart contracts, a research gap remains in effectively integrating diverse features of complex smart contracts with deep neural networks for enhanced detection. This paper presents SmartSecure, a vulnerability mining framework incorporating highâlevel semantic features extracted from contract source code. It provides inâdepth local insights into vulnerabilities through contract property graphs that integrate abstract syntax trees, control flow graphs, and data dependency graphs, encompassing all syntactic and semantic aspects of the contract function. To fortify these features, we integrate them with lowâlevel features derived from opcode sequences, encompassing global aspects. These diverse features are seamlessly fused and processed through a novel neural network design, resulting in a robust and effective solution. We evaluate our framework over 25,129 realâworld smart contracts. Extensive experiments demonstrate the superiority of our method over existing tools and neural networkâbased approaches. It achieves an exceptional performance level of up to 97.6%, marking a significant step forward in smart contract security.
Yan Pang, Xiangfu Liu, Teng Huang, Yile Hong · 7 authors
Smart contract vulnerabilities have led to significant economic losses, threatening blockchain security and development. Graph neural network (GNN)-based approaches, which capture the structural properties of contracts and leverage code dependencies to better understand contract behavior, have become widely used for vulnerability detection. However, these approaches face challenges in losing valuable information during graph construction and failing to capture rich semantic content, while traditional GNNs struggle with long-range dependencies and global context in complex contract graphs. To address these challenges, we propose ConSense, a GNN-based Contract Sensing Framework for Smart Contract Vulnerability Detection. ConSense comprises two core components: the smart contract graph generator, which constructs contract graphs while retaining both structural and semantic information, and ExploreFormer, which effectively integrates local and global context using advanced attention mechanisms for vulnerability detection. Comprehensive experimental evaluations were performed on the IR-ESCD and SCVHunter-SCD datasets. For instance, the IR-ESCD benchmarkâwhich encompasses eight distinct vulnerability categoriesâdemonstrates that ConSense attains an average detection accuracy of 97.74%, with a mean processing time of 0.648 seconds per contract. These results signify a statistically significant improvement over state-of-the-art methods in both precision and computational efficiency.