Due to the widespread application and economic value of smart contracts, they have become targets for attackers, leading to significant economic losses from vulnerabilities. Therefore, it is crucial to detect potential vulnerabilities in smart contracts before they are deployed. However, existing machine learning approaches often overlook the type information of nodes and edges, while those based on heterogeneous graphs only utilize the semantic information of smart contracts, neglecting the syntax structure information. This oversight compromises the performance in detecting vulnerabilities. To address these issues, we propose a novel smart contract vulnerability detection approach named HG-Detector(Heterogeneous Graph Detector), which stands for Heterogeneous Graph Detector. This approach integrates semantic and syntax structure information by employing a heterogeneous graph neural network to analyze the source code of smart contracts. It extracts both semantic and syntax structure information and then uses a classifier to detect potential vulnerabilities. Experimental results on a dataset comprising 1269 smart contracts show that, compared to MANDO, HG-Detector has achieved an average increase of 10.06% in Precision, an average increase of 1.61% in Recall, an average increase of 2.29% in the F1, and an average increase of 4.78% in Accuracy across seven types of vulnerabilities
Hanting Chu, Pengcheng Zhang, Hai Dong, Yan Xiao · 5 authors
Given that smart contracts execute transactions worth hundreds of millions of dollars daily, the issue of smart contract security has attracted considerable attention over the past few years. Traditional methods for detecting vulnerabilities heavily rely on manually developed rules and features, leading to the problems of low accuracy, high false positives, and poor scalability. Although deep learning-inspired approaches were designed to alleviate the problem, most of them rely on monothetic features, which may result in information incompetence during the learning process. Furthermore, the lack of available labeled vulnerability datasets is also a major limitation. To address these issues, we collect and construct a dataset of five labeled smart contract vulnerabilities, and proposeDeepFusion, a vulnerability detection method that fuses code representation information, including program slice information and abstraction syntax tree (AST) structured information. First, we develop automated tools to extract contract vulnerability slicing information from source code, and extract structured information from source code-converted AST. Second, code features and global structured features are fused into the data. Finally, the fused data are input into the Bidirectional Long Short-Term Memory+ Attention (BiLSTM+ATT) model for smart contract vulnerability detection. The BiLSTM model can capture long-term dependencies in both directions and is more suitable for processing serialized information generated byDeepFusion, while the attention mechanism can highlight the characteristic information of vulnerabilities. We conducted experiments via collecting a real smart contract dataset. The experimental results show that our method significantly outperforms the existing methods in detecting the vulnerabilities ofreentrancy,timestamp dependence,integer overflow and underflow,Use tx.origin for authentication, andUnprotected Self-destruct Instructionby 6.36%, 6.42%, 16.5%, 21.29%, and 25.05%, respectively. To the best of our knowledge, the latter two vulnerabilities are the first to be detected using deep learning methods.
With the rise of blockchain technology, the use of smart contracts has increased, alongside challenges in detecting and addressing unknown vulnerabilities. Existing systems face limitations, including inadequate manual testing and flaws in automated tools. To improve smart contract security, this study introduces a Hybrid Word Embedding (HyWE) method that combines Word2Vec, FastText, and GloVe models, augmented by a channel self-attention mechanism for enhanced feature extraction in the field of deep learning smart contract vulnerability detection. HyWE captures semantic and contextual relationships in code more accurately, aiding in precise vulnerability detection. The method involves preprocessing smart contract data, extracting features with various embeddings, and applying self-attention to highlight critical features. Applied within the SCVD-SA framework, HyWE’s performance was evaluated experimentally, demonstrating superior accuracy and efficiency in vulnerability detection. This method is intuitive but effective, and can be easily adapted to other models, increasing performance.
Smart contracts are self-executing agreements stored on the blockchain, widely used in finance, supply chain, IoT, and other fields. However, vulnerabilities in smart contract code can be exploited, leading to irreparable losses. Numerous smart contract vulnerability detection tools have been developed, with Slither being a prominent open-source static analysis tool. Despite its strengths, Slither suffers from false positives and false negatives. This paper introduces the SLLM system (Synergy of Slither and Large Language Models), which combines Slither with large language models (LLMs) like GPT-4. By leveraging pseudocode conversion and result feedback enhancement mechanisms, the system improves the accuracy of vulnerability detection. Experimental results show that SLLM outperforms Slither in reducing both false positives and false negatives across various common vulnerability types, demonstrating the effectiveness of integrating LLMs in smart contract static analysis.
With the advent of Bitcoin, virtual currency and blockchain technology are attracting attention, and the market is growing with the addition of the smart contract function of Blockchain 2.0. With the growth of the blockchain market, financial damage using the vulnerabilities of virtual currency and smart contracts is increasing. Recently, many studies have been conducted to detect smart contract vulnerabilities, and various methods using static and dynamic analysis exist. This paper proposes a method to detect smart contract vulnerabilities using static analysis and association mining techniques. From the experiment, we show that the performance of the proposed method is high compared to well-known open-source tools. We observe the effectiveness of static taint analysis for smart contract vulnerability detection. The proposed method shows high performance against reentrancy vulnerabilities. We expected that rapid response will be possible when a new type of vulnerability occurs in the future.
The integration of blockchain technology, particularly Ethereum and its smart contract, has revolutionized software programming. Solidity, Ethereum’s main language, is crucial due to its features for blockchain applications. However, the immutable nature of Smart Contract (SC) presents significant security issues, with vulnerabilities leading to financial risks. Meanwhile, Large language models (LLMS ) have transformed software development by enhancing coding efficiency and error detection. Despite their potential, current benchmarks often overlook niche languages like Solidity. This paper introduces the first benchmark to evaluate LLMs in Solidity smart contract generation, aiming to improve automated SC development and blockchain deployment reliability using a Test-Driven Development inspired methodology and pass@k metric. This work not only addresses a significant gap in LLM evaluation for blockchain applications but also extends the capabilities of LLMs in this specialized and critical area of software development.
There is a huge demand to ensure the compliance of smart contracts listed on blockchain platforms to safety and economic standards described in natural languages. Today, manual efforts in the form of auditing are commonly used to achieve this goal. ML-based automated techniques have the promise to alleviate human efforts and the resulting monetary costs. However, unlike other domains where ML techniques have had huge successes, no systematic ML techniques have been proposed or applied to smart contract auditing. We present SC-Bench, the first dataset for automated smart-contract auditing research. SC-Bench consists of 5,377 real-world smart contracts running on Ethereum, a widely used blockchain platform, and 15,975 violations of standards on Ehereum called ERCs. Out of these violations, 139 are real violations programmers made. The remaining are errors systematically injected by us to reflect the violations of different ERC rules. We evaluate SC-Bench using GPT-4 by prompting it with both the contracts and ERC rules. In addition, we manually identify each violated rule and the corresponding code site (i.e., oracle) and prompt GPT-4 with the information asking for a True-or-False question. Our results show that without the oracle, GPT-4 can only detect 0.9% violations, and with the oracle, it detects 22.9% violations. These results show the potential room for improvement in ML-based techniques for smart-contract auditing.
Smart contracts usually hold a large amount of digital assets, which can cause substantial losses if these contracts have vulnerabilities. Thus, it is essential to adequately detect possible vulnerabilities in smart contracts before deployment. There are many types of vulnerabilities in smart contracts, and different detection methods have their own unique advantages, some vulnerabilities may be more suitable for expert rule-based methods, while some vulnerabilities are more suitable for deep learning-based methods. A single detection method usually fails to fully use its ability to detect vulnerabilities. To address the above problems, we propose a composite approach named CDE-VD (Combining Deep Learning and Expert Rules for Smart Contract Vulnerability Detection) to improve the performance of vulnerability detection. The method divides smart contract samples into deep learning-prone sam-ples and expert rule-prone samples by classifying them before detection, and extracts expert rule features to train the smart contract detection method classifier to predict the category of the samples under analysis, then selects the suitable method for detection. The experimental results show that the vulnerability detection performance of CDE-VD outperforms that of single detection methods. Compared with the SOTA method MANDO, CDE-VD achieves average improvements of 3.22%, 2.32%, 9.25%, and 6.54% in terms of the Accuracy, Precision, Recall, and F1-score for five categories of vulnerabilities such as access control and time manipulation, respectively, which indicates that category prediction of the smart contract samples could improve vulnerability detection performance.
Dongcheng Li, W. Eric Wong, Xiaodan Wang, Sean Pan · 5 authors
This paper introduces a method for detecting vulnerabilities in smart contracts using static analysis and a multi-objective optimization algorithm. We focus on four types of vulnerabilities: reentrancy, call stack overflow, integer overflow, and timestamp dependencies. Initially, smart contracts are compiled into an abstract syntax tree to analyze relationships between contracts and functions, including calls, inheritance, and data flow. These analyses are transformed into static evaluations and intermediate representations that reveal internal relations. Based on these representations, we examine contract's functions, variables, and data dependencies to detect the specified vulnerabilities. To enhance detection accuracy and coverage, we apply a multi-objective optimization algorithm to the static analysis process. This involves assigning initial numeric values to input data and monitoring changes in statement coverage and detection accuracy. Using coverage and accuracy as fitness values, we calculate Pareto front and crowding distance values to select the best individuals for the new parent population, iterating until optimization criteria are met. We validate our approach using an open-source dataset collected from Etherscan, containing 6,693 smart contracts. Experimental results show that our method outperforms state-of-the-art tools in terms of coverage, accuracy, efficiency, and effectiveness in detecting the targeted vulnerabilities.
Smart contracts, as a form of digital protocol, are computer programs designed for the automatic execution, control, and recording of contractual terms. They permit transactions to be conducted without the need for an intermediary. However, the economic property of smart contracts makes their vulnerabilities susceptible to hacking attacks, leading to significant losses. In this paper, we introduce a smart contract timestamp vulnerability detection technique HomoDec based on code homogeneity. The core idea of this technique involves comparing the homogeneity between the code of the test smart contract and the existing smart contract vulnerability codes in the database to determine whether the tested code has a timestamp vulnerability. Specifically, HomoDec first explores how to vectorize smart contracts reasonably and efficiently, representing smart contract code as a high-dimensional vector containing features of code vulnerabilities. Subsequently, it investigates methods to determine the homogeneity between the test codes and the ones in vulnerability code base, enabling the detection of potential timestamp vulnerabilities in smart contract code.
Che Wang, Jiashuo Zhang, Jianbo Gao, L. Xia · 6 authors
Smart contracts are susceptible to being exploited by attackers, especially when facing real-world vulnerabilities. To mitigate this risk, developers often rely on third-party audit services to identify potential vulnerabilities before project deployment. Nevertheless, repairing the identified vulnerabilities is still complex and labor-intensive, particularly for developers lacking security expertise. Moreover, existing pattern-based repair tools mostly fail to address real-world vulnerabilities due to their lack of high-level semantic understanding. To fill this gap, we propose ContractTinker, a Large Language Models (LLMs)-empowered tool for real-world vulnerability repair. The key insight is our adoption of the Chain-of-Thought approach to break down the entire generation task into sub-tasks. Additionally, to reduce hallucination, we integrate program static analysis to guide the LLM. We evaluate ContractTinker on 48 high-risk vulnerabilities. The experimental results show that among the patches generated by ContractTinker, 23 (48%) are valid patches that fix the vulnerabilities, while 10 (21%) require only minor modifications. A video of ContractTinker is available at https://youtu.be/HWFVi-YHcPE.
Ethereum smart contracts, the new way of transactions and a popular name in the world of cryptocurrencies, have gathered a huge base of research and scientific attention. They are so helpful that they allow us to eliminate the need for a separate third-party library to allow unknown parties to see contract details on a computer. But since we can all see that online commerce is growing day by day and will continue to grow, it can never be fully free from scams and unethical operations. So, to correctly detect all such unethical and malicious transactions, this paper used a deep learning model. And to further enhance the model, this study used metaheuristic optimization as well. It employs an algorithm called Genetic Algorithm and to provide better optimization in the explorations phase of Cuckoo Search (CS) to achieve its goal of detecting fraudulent transactions. The algorithm covers the loopholes in the CS strategy. Furthermore, to provide strong grounds for research in our paper, this proposed model was compared with various types of approaches such as Light Gradient Boosting Machine, Support Vector Classification, Multi-Layer Perceptron, XGBoost, Logistic Regression, and Random Forest. The proposed model outperforms other significant models like SVC, KNN, LGBM Classifier, RF etc. with the accuracy of $\mathbf{9 8. 6 \%}$.
Ruichao Liang, Jing Chen, Cong Wu, Kun He · 9 authors
Smart contracts, the cornerstone of decentralized applications, have become increasingly prominent in revolutionizing the digital landscape. However, vulnerabilities in smart contracts pose great risks to user assets and undermine overall trust in decentralized systems. Fuzzing, a prominent security testing technique, is extensively explored to detect vulnerabilities. But current smart contract fuzzers fall short of expectations in testing efficiency for two primary reasons. Firstly, smart contracts are stateful programs, and existing approaches, primarily coverage-guided, lack effective feedback from the contract state. Consequently, they struggle to effectively explore the contract state space. Secondly, coverage-guided fuzzers, aiming for comprehensive program coverage, may lead to a wastage of testing resources on benign code areas. This wastage worsens in smart contract testing, as the mix of code and state spaces further complicates comprehensive testing. To address these challenges, we propose Vulseye, a stateful directed graybox fuzzer for smart contracts guided by vulnerabilities. Different from prior works, Vulseyeachieves stateful directed fuzzing by prioritizing testing resources to code areas and contract states that are more prone to vulnerabilities. We introduceCode TargetsandState Targetsinto fuzzing loops as the testing targets of Vulseye. We use static analysis and pattern matching to pinpointCode Targets, and propose a scalable backward analysis algorithm to specifyState Targets. We design a novel fitness metric that leverages feedback from both the contract code space and state space, directing fuzzing toward these targets. With the guidance of code and state targets, Vulseyealleviates the wastage of testing resources on benign code areas and achieves effective stateful fuzzing. In comparison with state-of-the-art fuzzers, Vulseyedemonstrated superior effectiveness and efficiency. Notably, it uncovered 4,845 vulnerabilities in 42,738 real-world smart contracts, outperforming existing approaches by up to$9.7\times $, and identified 11 previously unknown vulnerabilities within the top 50 Ethereum DApps, involving approximately 2,500,000 USD.
Smart contracts are decentralized applications de-ployed extensively on blockchain. Due to their economic nature, vulnerabilities in smart contracts can lead to potential significant economic and property losses, disrupting the stable ecosystem of Ethereum. Therefore, the detection of smart contract vul-nerabilities is of paramount importance. Current mainstream methods for smart contract vulnerability detection rely on heuris-tic algorithms based on manual design, which lack reusability across different application scenarios, are time-consuming, and exhibit suboptimal accuracy. To enhance vulnerability detection effectiveness, a method tailored for timestamp vulnerabilities in smart contracts is proposed, named SESCD, based on self-ensembling pretraining. The proposed approach first identifies potential data propagation paths for timestamp vulnerabilities, prunes them, and leverages self-ensembling pretrained models to learn about these propagation paths. Furthermore, the training process is optimized through knowledge distillation to improve the model's ability to detect whether smart contracts contain timestamp vulnerabilities. SESCD demonstrates superior vulner-ability detection and generalization capabilities, alleviating performance instability issues caused by insufficient training data. To validate the effectiveness of SESCD, comparative experiments are conducted on a real-world dataset of smart contracts against 13 mainstream smart contract vulnerability detection methods. Experimental results show that SESCD achieves precision, recall, and F1 scores of 0.91, 0.93, and 0.92 respectively in detecting timestamp vulnerabilities. Compared to the 13 mainstream methods, SESCD exhibits an average relative improvement of 28%, 30%, and 30%, significantly enhancing the detection capabilities of timestamp vulnerabilities.
Zhiyang Chen, Ye Liu, Sidi Mohamed Beillahi, Yi Li · 5 authors
Smart contracts, self-executing programs on the blockchain, facilitate reliable value exchanges without centralized oversight. Despite the recent focus on dynamic analysis of their transaction histories in both industry and academia, no open-source tool currently offers comprehensive tracking of complete transaction information to extract user-desired data such as invariant-related data. This paper introduces OpenTracer, designed to address this gap. OpenTracer guarantees comprehensive tracking of every execution step, providing complete transaction information. OpenTracer has been employed to analyze 350,800 Ethereum transactions, successfully inferring 23 different types of invariant from predefined templates. The tool is fully open-sourced, serving as a valuable resource for developers and researchers aiming to extract or validate new invariants from transaction traces. A demonstration video of OpenTracer is available at https://youtu.be/vTdmjWdYd30. The source code of OpenTracer is available at https://github.com/jeffchen006/OpenTracer.
NatSpec comments play an essential role in smart contracts. Their clear and informative format helps users gain an accurate understanding of smart contract functions and diminish financial risk. However, widespread non-adherence to NatSpec standards currently causes confusion for both end-users and developers. Current research often neglects the importance of NatSpec formats or solely emphasizes user-centric comments in smart contract generation. This oversight can hinder contract trustworthiness, code reusability, maintenance efficiency, and ultimately, the development of the community ecosystem. To bridge this gap, this paper presents the first empirical study on 253 verified contracts encompassing 16,620 functions from Etherscan, uncovering that 87 % of the smart contract functions have Comment Errors (CE) and pinpointing prevalent deviation patterns. Based on our findings, we propose CETerminator, an automated approach for detecting and rectifying CE in smart contract functions. Due to the scarcity of NatSpec-compliant comments for collected smart contract functions, CETerminator employs in-context learning on a large language model to generate NatSpec comments. The approach then compares the original and the generated comments, utilizing corpus-driven heuristic rules to identify and correct diverse error categories in the original comments. In our evaluation, CETerminator demonstrates a high token overlap rate for addressing missing comments. In addition, the average precision, recall, and F1-scores for handling inconsistency comments are 85.28 %, 86.48 %, and 85.85%, respectively, outperforming the baseline by 39.79%, 39.53%, and 39.84%.
Emanuele Antonio Napoli, Fadi Barbà ra, Valentina Gatteschi, Claudio Schifanella
In the rapidly evolving landscape of blockchain technology, smart contracts stand as pivotal instrument for automating and enforcing digital agreements. However, their creation often necessitates specialized programming skills, hindering broader adoption and accessibility. This paper proposes a pipeline that leverages the capabilities of Large Language Models (LLMs) to automate the generation of smart contracts. By harnessing the natural language understanding and generation capabilities of LLMs, our approach aims to make accessible smart contract development to people that are not familiar with this task. The proposed pipeline employs the CO-STAR methodology to optimize prompt creation for high-quality outputs. Moreover, in order to assess the correctness and reliability of the generated smart contracts, we leverage on Slither, one of the most cutting-edge vulnerability detection tools. Furthermore, we propose a benchmarking suite based on metrics such as compilability, vulnerabilities, and presence of comments, among the others, in order to evaluate the effectiveness of the pipeline in terms of consistency of generated smart contracts, LLM's temperature effect, and prompt selection. The results show that our pipeline is able to produce 98.1% of compilable smart contracts, the temperature value has negligible effect on the generated smart contracts, and the CO-STAR methodology produces valuable and consistent outputs with low-impact vulnerabilities.
This study analyzes the application of code-generating Large Language Models in the creation of immutable Solidity smart contracts on the Ethereum Blockchain. Other works have previously analyzed Artificial Intelligence code generation abilities. This paper aims to expand this to a larger scope to include programs where security and efficiency are of utmost priority such as smart contracts. The hypothesis leading into the study was that LLMs in general would have difficulty in rigorously implementing security details in the code, which was shown through our results, but surprisingly generally succeeded in many common types of contracts. We also discovered a novel way of generating smart contracts through new prompting strategies.
Bo Gao, Qingsong Wei, Yong Liu, Rick Siow Mong Goh
Smart contracts are becoming an integral part of decentralized applications, yet exploitable bugs in these contracts pose significant threats, often leading to considerable monetary losses. Traditional tools often struggle to identify these bugs, with a recent study indicating that 80% of them are classified as Machine Unauditable Bugs (MUBs), rendering conventional approaches ineffective in addressing such cases. In practice, identifying MUBs requires seasoned expertise and is time-intensive, often stalling project progress. In this work, we present a preliminary evaluation of the performance of ChatGPT, a state-of-the-art large language model, especially in detecting MUBs. Our study first investigates the effectiveness and limitations of ChatGPT in detecting various categories of MUBs with two kinds of prompts, general prompts and guidance prompts, on 246 real-world MUBs collected from Code4rena between 2021 and 2022. Subsequently, we compared the leading tool, SPCON, with ChatGPT on 17 CVE contracts with access control issues (a category of MUBs), and found that ChatGPT exhibited comparable performance but better usability over SPCON. We summarize the implications of our findings for the broader community, shedding light on the model’s capabilities, limitations and potentials in detecting smart contract bugs. Our evaluation dataset and results are released at Github1.
SymboleoNLP is a Web-based tool that allows contract authors to make customizations to a legal contract template using a controlled, yet expressive, natural language. The tool also maintains a formal specification of the contract in Symboleo, a formal specification language designed for the legal contract monitoring domain. The controlled customizations allow for the automated formalization of the customized contract, enabling Symboleo-based property verification and code generation of monitoring smart contracts. This work pushes the boundaries of requirements-based contract template customization with a view towards full formalization.
In the quickly changing world of blockchain technology, it is critical to guarantee the security of the self-executing contracts, written in programming languages like Solidity called smart contracts. Not all security vulnerabilities in smart contracts will be found by human code reviews and security audits using traditional methods. Deep learning networks have become a promising answer to this problem. In this paper, we present the architecture of two models—using convolutional and recurrent neural networks—that are intended to effectively discover five vulnerabilities in smart contracts. To train and validate the models, we used a dataset that includes 106474 audited smart contracts taken from the public Ethereum blockchain. Instead of the source code that is typically used by most deep learning-based solutions, the models receive input in the form of Ethereum Virtual Machine (EVM) bytecode. Across all five vulnerabilities, the Recurrent Neural Network model has an average micro F1-score of 0.93, whereas the Convolutional Neural Network achieves an average micro F1-score of 0.89. Through comparative research with various deep learning systems and static analysis tools, we have determined that EVM bytecode may be leveraged as a feature to detect vulnerabilities in smart contracts.
Large language models (LLMs) have showcased remarkable skills, rivaling or even exceeding human intelligence in certain areas. Their proficiency in translation is notable, as they may replicate the nuanced, preparatory steps of human translators for high-quality outcomes. Although there have been some notable work exploring using LLMs for code to code translation, there has not been one for smart contracts, especially when a target language is unseen to the LLM. In this work, we aim to introduce our novel framework SolMover consisting of two different LLMs working in tandem in a framework to understand coding concepts and then use that to translate code to an unseen language. We explore the human-like learning capability of LLMs in this paper with a detailed evaluation of the methodology to translate existing smart contracts from Solidity to a low-resource one called Move. Specifically, we enable one LLM to understand coding rules for the new language to generate a planning task, for the second LLM to follow, which does not have planning capability but does have coding. Experiments show that SolMOver brings significant improvement over gpt-3.5-turbo-1106 and outperforms both Palm2 and Mixtral-8x7B-Instruct. Our further analysis shows us that employing our bug mitigation technique even without the framework still improves code quality for all models.
With the rapid advancement of technology, the emergence of Non-Fungible Token (NFT) platforms has revolutionized digital buying and selling. However, this innovative platform has also given rise to a concerning issue: the unintentional trade of personal data instead of artwork. This problem poses a significant challenge in protecting individuals' personal information, especially when items like National Identity Card (KTP) photos are sold as NFT assets. This research aims to explore the critical importance of legal education in safeguarding personal data, thus preventing such transactions that may lead to self-harm. Employing a normative juridical method and a conceptual approach, this study extensively analyzes legal aspects and regulations related to personal data protection. The findings underscore the urgent need for legal education to effectively address personal data transactions on NFT sites within marketplace platforms. Despite the implementation of the Personal Data Protection Act (Law Number 27 of 2022), it is clear that the legislation alone is insufficient. Given the gravity of the issue, comprehensive public education initiatives involving various segments of society are crucial. Protecting personal data has become a matter of utmost concern for the government, the state, NFT platform users, and internet users at large. Individuals must adopt a vigilant and proactive approach in safeguarding their personal data. Legal education programs, including outreach activities conducted by governmental and non-governmental entities, along with the involvement of students and academics in community counseling, can effectively support this objective.