Advanced Smart Contract Vulnerability Detection via LLM-Powered Multi-Agent Systems

Ethereum smart contracts are a special type of computer programs. Once deployed on the blockchain, they cannot be modified. This presents a significant challenge to the security of smart contracts. Previous research has proposed static and dynamic detection tools to identify vulnerabilities in smart contracts. These tools check contract vulnerabilities based on predefined rules, and the accuracy of detection strongly depends on the design of the rules. However, the constant emergence of new vulnerability types and strategies for vulnerability protection leads to numerous false positives and false negatives by tools. To address this problem, we analyze the characteristics of vulnerabilities in smart contracts and the corresponding protection strategies. We convert the contracts' bytecode into an intermediate representation to extract semantic information of the contracts. Based on this semantic information, we establish a set of detection rules based on semantic facts and implement a vulnerability detection tool SafeCheck using static program analysis methods. The tool is used to detect six common types of vulnerabilities in smart contracts. We have extensively evaluated SafeCheck on real Ethereum smart contracts and compared it to other tools. The experimental results show that SafeCheck performs better in smart contract vulnerability detection compared to other typical tools, with a high F‐measure (up to 83.1%) for its entire dataset.

Reentrancy vulnerability as one of the most notorious vulnerabilities, has been a prominent topic in smart contract security research. Research shows that existing vulnerability detection presents a range of challenges, especially as smart contracts continue to increase in complexity. Existing tools perform poorly in terms of efficiency and successful detection rates for vulnerabilities in complex contracts. To effectively detect reentrancy vulnerabilities in contracts with complex logic, we propose a tool named SliSE. SliSE’s detection process consists of two stages: Warning Search and Symbolic Execution Verification . In Stage 1, SliSE utilizes program slicing to analyze the Inter-contract Program Dependency Graph (I-PDG) of the contract, and collects suspicious vulnerability information as warnings. In Stage 2, symbolic execution is employed to verify the reachability of these warnings, thereby enhancing vulnerability detection accuracy. SliSE obtained the best performance compared with eight state-of-the-art detection tools. It achieved an F1 score of 78.65%, surpassing the highest score recorded by an existing tool of 9.26%. Additionally, it attained a recall rate exceeding 90% for detection of contracts on Ethereum. Overall, SliSE provides a robust and efficient method for detection of Reentrancy vulnerabilities for complex contracts.

While Ethereum smart contracts provide users with transfer and transaction services, vulnerabilities in smart contracts are constantly damaging users’ property and user experience. At present, many detection methods for smart contract vulnerabilities have been proposed, but these methods have not fully analyzed the information of multiple modalities of smart contracts, and their effectiveness in detecting long smart contracts is not ideal. We propose a lightweight Ethereum smart contract vulnerability detection method based on bimodal and hierarchical attention to address this issue. This method can combine the source code and opcode of smart contracts for analysis, and use a hierarchical attention network composed of bidirectional GRU and attention mechanism for vulnerability feature extraction. The experimental results show that in the task of detecting vulnerabilities in long smart contracts, this method has better detection capabilities for four types of vulnerabilities: Denial of Service, Reentrancy, Arithmetic, and Timestamp Dependency, compared to the most advanced deep learning smart contract vulnerability detection methods currently available.

In recent years, the second-generation blockchain platforms and applications represented by smart contracts have seen explosive growth, but frequent smart contract vulnerability incidents have seriously threatened the ecological security of blockchain. In view of the low efficiency of code audit based on expert experience, it is important to develop a general automation tool to mine smart contract vulnerabilities. In the beginning, the security threats of smart contracts should be investigated and analyzed, and many smart contract vulnerabilities and attack modes that occur frequently, such as code reentrant, access control, integer overflow, etc., were summarized. Then, the technology method of smart contract vulnerability detection conforming to The Times is obtained, and the current samples of smart contract vulnerability detection are summarized. The current investigation includes too few types of vulnerabilities, with a variety of inaccuracies and deviations. It is only carried out through manual audit. Through these methods, according to the state of including after put forward the general ideas of this kind of situation, and puts forward a kind of symbolic execution auxiliary fuzzy test framework, can reduce the symbolic execution channel congestion and fuzzy test code coverage degree is too little, so as to improve test efficiency, easy to dig holes of large and medium-sized intelligent contracts quality improvement.KeywordsBlockchain securitySmart contractVulnerability detectionFuzzy testingVulnerability mining

The financial property of Ethereum makes smart contract attacks frequently bring about tremendous economic loss. Method for effective detection of vulnerabilities in contracts imperative. Existing efforts for contract security analysis heavily rely on rigid rules defined by experts, which are labor-intensive and non-scalable. There is still a lack of effort that considers combining expert-defined security patterns with deep learning. This paper proposes EtherGIS, a vulnerability detection framework that utilizes graph neural networks (GNN) and expert knowledge to extract the graph feature from smart contract control flow graphs (CFG). To gain multi-dimensional contract information and reinforce the attention of vulnerability-related graph features, sensitive EVM instruction corpora are constructed by analyzing EVM underlying logic and diverse vulnerability triggering mechanisms. The characteristic of nodes and edges in a CFG is initially confirmed according to the corpora, generating the corresponding attribute graph. GNN is adopted to aggregate the whole graph's attribute and structure information, bridging the semantic gap between low-level graph features and high-level contract features. The feature representation of the graph is finally input into the graph classification model for vulnerability detection. Furthermore, automated machine learning (AutoML) is adopted to automate the entire deep learning process. Data for this research was collected from Ethereum to build up a dataset of six vulnerabilities for evaluation. Experimental results demonstrate that EtherGIS can productively detect vulnerabilities in Ethereum smart contracts in terms of accuracy, precision, recall, and F1-score. All aspects outperform the existing work.

A smart contract is a computer protocol intended to digitally facilitate and enforce the negotiation of a contract in undependable environment. However, the number of attacks using the vulnerabilities of the smart contracts is also growing in recent years. Many solutions have been proposed in order to deal with them, such as documenting vulnerabilities or setting the security strategies. Among them, the most influential progress is made by the formal verification method. In this paper, we propose a formal verification method based on Colored Petri Nets (CPN) to verify smart contracts in blockchain system. First, we develop the smart contract models with possible attacker models based on hierarchical CPN modeling, then the smart contract models are executed by step-by-step simulation to validate their functional correctness, and finally we utilize the branch timing logic ASK-CTL based model checking technology in the CPN tools to detect latent vulnerabilities in smart contracts. We demonstrate that our CPN modeling based verification method can not only detect the logical vulnerabilities of the smart contract, but also consider the impacts of users behavior to find out potential non-logical vulnerabilities in the contracts, such as the vulnerabilities caused by the limitations of the Solidity language.

Smart contracts have significant losses due to various types of vulnerabilities. However, traditional vulnerability detection methods rely extensively on expert rules, resulting in low detection accuracy and poor adaptability to novel attacks. To address these problems, in this paper, deep learning methods are combined with smart contract vulnerability code detection approaches. syntax trees (ASTs), which are special isomorphic graph structures, are an important bridge between source code and graph neural networks. By learning the AST, the model can understand the semantics of the source code. Moreover, graph neural networks have an increasing ability to address complex heterogeneous graphs. Therefore, control flow graphs are fused with data flow graphs on the basis of the ASTs to build heterogeneous graphs with richer code semantics. Furthermore, multigranularity analysis of the vulnerability detection results is performed, including coarse-grained contract-level vulnerability detection and fine-grained line-level vulnerability detection. Through this multigranularity detection approach, vulnerabilities in contracts can be identified and analysed more comprehensively, providing a richer perspective and more solutions for vulnerability detection. The experimental results show that the proposed multigranularity vulnerability detection method based on heterogeneous graphs (MVD-HG) improves both the accuracy and range of the detected vulnerability types in contract-level vulnerability detection tasks; moreover, in the line-level vulnerability detection task, the MVD-HG model achieves significant results and addresses the shortcomings of existing methods. In addition, based on code generation methods used in related fields, a data enhancement method based on the source code is developed, which effectively expands the experimental dataset to address the reduced credibility of the results due to insufficient amounts of data.

Smart contracts are decentralized applications running on Blockchain. A very large number of smart contracts has been deployed on Ethereum. Meanwhile, security flaws of contracts have led to huge pecuniary losses and destroyed the ecological stability of contract layer on Blockchain. It is thus an emerging yet crucial issue to effectively and efficiently detect vulnerabilities in contracts. Existing detection methods like Oyente and Securify are mainly based on symbolic execution or analysis. These methods are very time-consuming, as the symbolic execution requires the exploration of all executable paths or the analysis of dependency graphs in a contract. In this work, we propose ContractWard to detect vulnerabilities in smart contracts with machine learning techniques. First, we extract bigram features from simplified operation codes of smart contracts. Second, we employ five machine learning algorithms and two sampling algorithms to build the models. ContractWard is evaluated with 49502 real-world smart contracts running on Ethereum. The experimental results demonstrate the effectiveness and efficiency of ContractWard. The predictive Micro-F1 and Macro-F1 of ContractWard are over 96% and the average detection time is 4 seconds on each smart contract when we use XGBoost for training the models and SMOTETomek for balancing the training sets.

Digital assets involved in smart contracts are on the rise. Security vulnerabilities in smart contracts have resulted in significant losses for the blockchain community. Existing smart contract vulnerability detection techniques have been typically single-purposed and focused only on the source code or opcode of contracts. This paper presents a new smart contract vulnerability detection method, which extracts features from different levels of smart contracts to train machine learning models for effective detection of vulnerabilities. Specifically, we propose to extract 2-gram features from the opcodes of smart contracts and token features from the source code using a pre-trained CodeBERT model, thereby capturing the semantic information of smart contracts at different levels. The 2-gram and token features are separately aggregated and then fused and input into machine-learning models to mine the vulnerability features of contracts. Over 10,266 smart contracts are used to verify the proposed method. Widespread reentrancy, timestamp dependence, and transaction-ordering dependence vulnerabilities are considered. Experiments show the fused features can help significantly improve smart contract vulnerability detection compared to the single-level features. The detection accuracy is as high as 98%, 98% and 94% for the three vulnerabilities, respectively. The average detection time is 0.99 second per contract, indicating the proposed method is suitable for automatic batch detection of vulnerabilities in smart contracts.

Attacks on transactions of Ethereum could be dangerous because they could lead to a big loss of money. There are many tools detecting vulnerabilities in smart contracts trying to avoid potential attacks. However, we found that there are still many missed vulnerabilities in contracts. Motivated by this, we propose a methodology to reinforce EVM to stop dangerous transactions in real time even when the smart contract contains vulnerabilities. Basically, the methodology consists of three steps: monitoring strategy definition, opcode-structure maintenance and EVM instrumentation. Monitoring strategy definition refers to the specific rule to test whether there is a dangerous operation during transaction execution. Opcode-structure maintenance is to maintain a structure to store the rule related opcodes and analyze it before an operation execution. EVM instrumentation inserts the monitoring strategy, interrupting mechanism and the opcode-structure operations in EVM source code. For evaluation, we implement EVM <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">*</sup> on js-evm, a widely-used EVM platform written in javascript. We collect 10 contracts online with known bugs and use each contract to execute a dangerous transaction, all of them have been interrupted by our reinforced EVM <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">*</sup> , while the original EVM permits all attack transactions. For the time overhead, the reinforced EVM <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">*</sup> is slower than the original one by 20-30%, which is tolerable for the financial critical applications.

With the development of blockchain technology, more and more attention has been paid to the intersection of blockchain and education, and various educational evaluation systems and E-learning systems are developed based on blockchain technology. Among them, Ethereum smart contract is favored by developers for its "event-triggered" mechanism for building education intelligent trading systems and intelligent learning platforms. However, due to the immutability of blockchain, published smart contracts cannot be modified, so problematic contracts cannot be fixed by modifying the code in the educational blockchain. In recent years, security incidents due to smart contract vulnerabilities have caused huge property losses, so the detection of smart contract vulnerabilities in educational blockchain has become a great challenge. To solve this problem, this paper proposes a graph neural network (GNN) based vulnerability detection for smart contracts in educational blockchains. Firstly, the bytecodes are decompiled to get the opcode. Secondly, the basic blocks are divided, and the edges between the basic blocks according to the opcode execution logic are added. Then, the control flow graphs (CFG) are built. Finally, we designed a GNN-based model for vulnerability detection. The experimental results show that the proposed method is effective for the vulnerability detection of smart contracts. Compared with the traditional approaches, it can get good results with fewer layers of the GCN model, which shows that the contract bytecode and GCN model are efficient in vulnerability detection.

Smart contracts are nowadays at the core of most blockchain systems. Like all computer programs, smart contracts are subject to the presence of residual faults, including severe security vulnerabilities. However, the key distinction lies in how these vulnerabilities are addressed. In smart contracts, when a vulnerability is identified, the affected contract must be terminated within the blockchain, as due to the immutable nature of blockchains, it is impossible to patch a contract once deployed. In this context, research efforts have been focused on proactively preventing the deployment of smart contracts containing vulnerabilities, mainly through the development of vulnerability detection tools. Along with these efforts, several heterogeneous vulnerability classification schemes appeared (e.g., most notably DASP and SWC). At the time of writing, these are mostly outdated initiatives, even though new smart contract vulnerabilities are consistently uncovered. In this paper, we propose OpenSCV, a new and Open hierarchical taxonomy for Smart Contract vulnerabilities, which is open to community contributions and matches the current state of the practice while being prepared to handle future modifications and evolution. The taxonomy was built based on the analysis of the existing research on vulnerability classification, community-maintained classification schemes, and research on smart contract vulnerability detection. We show how OpenSCV covers the announced detection ability of the current vulnerability detection tools and highlight its usefulness in smart contract vulnerability research. To validate OpenSCV, we performed an expert-based analysis wherein we invited multiple experts engaged in smart contract security research to participate in a questionnaire. The feedback from these experts indicated that the categories in OpenSCV are representative, clear, easily understandable, comprehensive, and highly useful. Regarding the vulnerabilities, the experts confirmed that they are easily understandable.

Vulnerabilities in smart contracts may trigger serious security events, and the detection of smart contract vulnerabilities has become a significant problem. In this paper, to solve the limitations of current deep learning-based vulnerability detection methods in extracting various code critical features, using the multi-scale cascade encoder architecture as the backbone, we propose a novel Multi-Scale Encoder Vulnerability Detection (MEVD) approach to hit well-known high-risk vulnerabilities in smart contracts. Firstly, we use the gating mechanism to design a unique Surface Feature Encoder (SFE) to enrich the semantic information of code features. Then, by combining a Base Transformer Encoder (BTE) and a Detail CNN Encoder (DCE), we introduce a dual-branch encoder to capture the global structure and local detail features of the smart contract code, respectively. Finally, to focus the model’s attention on vulnerability-related characteristics, we employ the Deep Residual Shrinkage Network (DRSN). Experimental results on three types of high-risk vulnerability datasets demonstrate performance compared to state-of-the-art methods, and our method achieves an average detection accuracy of 90%.

A vulnerability detection framework by focusing on critical execution paths

Blockchain presents a chance to address the security and privacy issues of the Internet of Things; however, blockchain itself has certain security issues. How to accurately identify smart contract vulnerabilities is one of the key issues at hand. Most existing methods require large-scale data support to avoid overfitting; machine learning (ML) models trained on small-scale vulnerability data are often difficult to produce satisfactory results in smart contract vulnerability prediction. However, in the real world, collecting contractual vulnerability data requires huge human and time costs. To alleviate these problems, this paper proposed an ensemble learning (EL)-based contract vulnerability prediction method, which is based on seven different neural networks using contract vulnerability data for contract-level vulnerability detection. Seven neural network (NN) models were first pretrained using an information graph (IG) consisting of source datasets, which then were integrated into an ensemble model called Smart Contract Vulnerability Detection method based on Information Graph and Ensemble Learning (SCVDIE). The effectiveness of the SCVDIE model was verified using a target dataset composed of IG, and then its performances were compared with static tools and seven independent data-driven methods. The verification and comparison results show that the proposed SCVDIE method has higher accuracy and robustness than other data-driven methods in the target task of predicting smart contract vulnerabilities.