The security of smart contracts has garnered considerable attention given the potential for substantial financial losses and erosion of trust in blockchain platforms. Numerous methods have been proposed to detect vulnerabilities in smart contracts. Notably, as the number of smart contracts continues to proliferate, automated techniques based on deep learning (DL) are making remarkable progress. However, a significant challenge persists in acquiring an efficient embedding representation that is compatible with DL models with input length restrictions. In this paper, we propose a novel detection method named GraBit for identifying reentrancy vulnerability-one of the most critical vulnerabilities in smart contracts. GraBit leverages the pre-trained model GraphCodeBERT to embed both the source code and concise key data flow graphs extracted from the code. Additionally, we customize a sequential model based on Bi-directional Long Short-Term Memory and attention mechanism to effectively capture contextual semantic information. To evaluate the performance of GraBit, we conduct extensive experiments on a public large-scale dataset. Our experimental results reveal that GraBit achieves a remarkable F1-score of 94.44% in detecting reentrancy vulnerability, outperforming state-of-the-art methods.
The Ponzi scheme implemented through smart contracts is one of the most common scams on the blockchain platform. Although various learning-based Ponzi smart contract detection approaches have been proposed, they still suffer from several limitations, i.e., 1) extracting insufficient semantics and gathering Ponzi irrelevant components from the smart contract during feature engineering, and 2) underutilizing structured semantic features during model training. As the Ponzi scheme is an economic crime with the typical Rob-Peter-to-Pay-Paul transaction pattern, we propose a transaction semantic learning based approach to mitigate the above limitations. The fundamental idea of our approach is to represent the transaction-related semantics of a smart contract as a graph and utilize a graph convolutional network (GCN) to learn the potential Ponzi-like transaction pattern from it. We define a novel code representation named slice transaction property graph (sTPG) to represent the transaction-related semantics, which can encode multiple transaction-related semantics inside a smart contract function into a graph and eliminate other irrelevant fragments. Then, we propose a relation-sensitive GCN as the learning model to identify potential Ponzi-scheme-like transaction patterns from sTPG by considering both nodes and edges features in sTPG. We evaluate our approach on two datasets: 1) smart contracts collected from Forum and Public datasets, and 2) really deployed smart contracts on the Ethereum blockchain. The experiment results show that our approach outperforms the state-of-the-art learning-based approaches.
Lei Yu, Junyi Lu, Xianglong Liu, Yang Li · 6 authors
With the increasing security issues in the blockchain, smart contract vulnerability detection has gradually become the focus of research. Recently, many approaches have been proposed to detect smart contract vulnerabilities. Despite promising results, these approaches still have three drawbacks: 1) Symbolic execution and static analysis methods are constrained by predefined rules, which limits their adaptability to different vulnerabilities. 2) Most smart contract code contains abundant irrelevant information which is useless for vulnerability detection. 3) Pre-trained models fail to bridge the gap between pre-training and detecting smart contract vulnerabilities.To solve these problems, we propose an approach named PSCVFinder for detecting reentrancy vulnerability and times-tamp dependency vulnerability, which are two severe vulnerabilities in smart contract. To better detect these vulnerabilities, we propose CSCV which is a smart contract slicing method to reduce the irrelevant code. Unlike existing approaches, our model first learns the representation of programming language through the pre-training model, then fully exploits the capacity of large language model with prompt-tuning to precisely detect smart contract vulnerability. We conduct experiments on real-world dataset and the results reflect that PSCVFinder scores 93.83% and 93.49% on two kinds of vulnerabilities in F1-score, surpassing the state-of-the-art baseline by 1.14% and 4.02%, respectively.
Chuyi Yan, Chen Zhang, Meng Shen, Ning Li · 8 authors
Abstract Ethereum’s high attention, rich business, certain anonymity, and untraceability have attracted a group of attackers. Cybercrime on it has become increasingly rampant, among which scam behavior is convenient, cryptic, antagonistic and resulting in large economic losses. So we consider the scam behavior on Ethereum and investigate it at the node interaction level. Based on the life cycle and risk identification points we found, we propose an automatic detection model named Aparecium . First, a graph generation method which focus on the scam life cycle is adopted to mitigate the sparsity of the scam behaviors. Second, the life cycle patterns are delicate modeled because of the crypticity and antagonism of Ethereum scam behaviors. Conducting experiments in the wild Ethereum datasets, we prove Aparecium is effective which the precision, recall and F1-score achieve at 0.977, 0.957 and 0.967 respectively.
<p>The <a href="https://sites.google.com/99cryptowallet.com/ledgerwalletextension/"><strong>Ledger Wallet Extension</strong></a> is a multi-chain web browser extension developed to offer secure and straightforward access to Web3 through the Ledger hardware wallet, letting you connect with dApps (decentralized applications) directly and simply without importing your Ledger account into the software wallet. Read the guide to understand the ins and outs of setting up and utilizing the Ledger Wallet Extension.</p>
Abstract With the rapid development of blockchain technology in the financial sector, the security of blockchain is being put to the test due to an increase in phishing fraud. Therefore, it is essential to study more effective measures and better solutions. Graph models have been proven to provide abundant information for downstream assignments. In this study, a graph‐based embedding classification method is proposed for phishing detection on Ethereum by modeling its transaction records using subgraphs. Initially, the transaction data of normal addresses and an equal number of confirmed phishing addresses are collected through web crawling. Multiple subgraphs using the collected transaction records are constructed, with each subgraph containing a target address and its nearby transaction network. To extract features of the addresses, a modified Graph2Vec model called imgraph2vec is designed, which considers block height, timestamp, and amount of transactions. Finally, the Extreme Gradient Boosting (XGBoost) algorithm is employed to detect phishing and normal addresses. The experimental results show that the proposed method achieves good performance in phishing detection, indicating the effectiveness of imgraph2vec in feature acquisition of transaction networks compared to existing models.
Blockchain technology revolutionizes the Internet, but also poses increasing risks, particularly in cryptocurrency finance. On the Ethereum platform, Ponzi schemes, phishing scams, and a variety of other frauds emerge. Existing Ponzi scheme detection approaches based on heterogeneous transaction graph modeling leverages semantic information between node (account) pairs to establish connections, overlooking the semantic attributes inherent to the edges (interactions). To overcome this, we construct heterogeneous Ethereum interaction graphs with multiple triplet interaction patterns to better depict the real Ethereum environment. Based on this, we design a new framework named multi-triplet augmented heterogeneous graph neural network (MAHGNN) for Ponzi scheme detection. We introduce the Conditional Variational Auto Encoder (CVAE) to capture the semantic information of different triplet interaction patterns, which facilitates the characterization on account features. Extensive experiments demonstrate that MAHGNN is capable of addressing the problem of multi-edge interactions in heterogeneous Ethereum interaction graphs and achieving state-of-the-art performance in Ponzi scheme detection.
Health care data requires data secrecy, confidentiality, and distribution through public networks. Blockchain is the latest and most secure framework through which health care data can be transferred on the public network. Blockchain has gained attention in recent year’s due to its decentralized, distributed, and immutable ledger framework. However, Blockchain is also susceptible to many attacks in the permission less network, one such attack is known as Sybil attack, where several malicious nodes are created by the single node and gain multiple undue advantages over the network. In this research work, the Blockchain network is created using the smart contract method which gets hampered due to Sybil attack. Thus, a novel method is proposed to prevent Sybil attack in the network for privacy preservation. Universal Unique Identifier code is used for identification and prevention of the Sybil attack in the self-created networks. Results depict that proposed method correctly identifies the chances of attack and the prevention from the attack. The approach has been evaluated on performance metrics namely, true positive rate and accuracy which were attained as 87.5 % and 91% respectively, in the small network. This demonstrates that the proposed work attains improved results as compared to other latest available methods.
The rapid growth of blockchain technology hasintroduced newsecurity challengesin decentralized systems.In this paper, we present Block-AD, a Blockchain Attack-Defense Capture The Flag (CTF) competition aimed at improving smart contract security skills and addressing evolving security threats in Next-Web3 environments. Unlike traditional CTF competitions, participants engage in attack and defense actions to exploit vulnerabilities and protect their smart contract services. This game-based approach concludes with rewards distributed from the competition’s vault and the allocation of non-fungible tokens (NFTs) as proof of participation. This approach aims to provide a fun and engaging way to improve the security skills of all participants, as well as to identify and fix vulnerabilities in smart contracts. By combining blockchain technology, CTF methodology, and Next-Web3 security, Block-AD provides a unique and innovative approach for enhancing cybersecurity skills in decentralized systems and smart contracts.
Abstract Deanonymization is one of the major research challenges in the Bitcoin blockchain, as entities are pseudonymous and cannot be identified from the on-chain data. Various approaches exist to identify multiple addresses of the same entity, i.e., address clustering. But it is known that these approaches tend to find several clusters for the same actor. In this work, we propose to assign a fingerprint to entities based on the dynamic graph of the taint flow of money originating from them, with the idea that we could identify multiple clusters of addresses belonging to the same entity as having similar fingerprints. We experiment with different configurations to generate substructure patterns from taint flows before embedding them using representation learning models. To evaluate our method, we train classification models to identify entities from their fingerprints. Experiments show that our approach can accurately classify entities on three datasets. We compare different fingerprint strategies and show that including the temporality of transactions improves classification accuracy and that following the flow for too long impairs performance. Our work demonstrates that out-flow fingerprinting is a valid approach for recognizing multiple clusters of the same entity.
Zhutian Lin, Xi Xiao, Guangwu Hu, Bin Zhang · 6 authors
The exponential growth of Ethereum transactions has resulted in a significant increase in phishing scams, leading to substantial financial losses in recent years. Current machine/deep learning-based approaches for classification have been found to be inadequate for large-scale and label-imbalanced Ethereum scenarios. To address this issue, we propose Phish2vec, a novel network embedding approach that takes into account the transaction temporality and heterogeneity in detecting phishing scams on Ethereum. Our approach begins by producing a transaction sub-network through data collection and preprocessing, which includes a novel Statistics-Based Sampling (SBS) method to address label leakage. To generate sequences that contain more comprehensive information, we then utilize two different types of sequences generators: Temporal-based Sequences Generator (TSG) and Heterogeneous-based Sequences Generator (HSG). By concatenating the sequences generated by TSG and HSG together, and feeding them into Word2vec and Fully Connected neural network (FC), our approach can identify phishing accounts with an Fl-score as high as 82.05%, which significantly outperforms classic schemes such as DeepWalk (67.29%), Trans2vec (74.78%), and Node2vec (70.91%).
Multiple works have leveraged the public Bitcoin ledger to estimate the revenue cybercriminals obtain from their victims. Estimations focusing on the same target often do not agree, due to the use of different methodologies, seed addresses, and time periods. These factors make it challenging to understand the impact of their methodological differences. Furthermore, they underestimate the revenue due to the (lack of) coverage on the target's payment addresses, but how large this impact remains unknown. In this work, we perform the first systematic analysis on the estimation of cybercrime bitcoin revenue. We implement a tool that can replicate the different estimation methodologies. Using our tool we can quantify, in a controlled setting, the impact of the different methodology steps. In contrast to what is widely believed, we show that the revenue is not always underestimated. There exist methodologies that can introduce huge overestimation. We collect 30,424 payment addresses and use them to compare the financial impact of 6 cybercrimes (ransomware, clippers, sextortion, Ponzi schemes, giveaway scams, exchange scams) and of 141 cybercriminal groups. We observe that the popular multi-input clustering fails to discover addresses for 40% of groups. We quantify, for the first time, the impact of the (lack of) coverage on the estimation. For this, we propose two techniques to achieve high coverage, possibly nearly complete, on the DeadBolt server ransomware. Our expanded coverage enables estimating DeadBolt's revenue at $2.47M, 39 times higher than the estimation using two popular Internet scan engines.
Sep 7, 2023·2023 IEEE 12th International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS)
In this paper we analyze how and why new emerging technologies originally developed outside security fields such as Blockchain and Large Language Models (LLMs) can and may impact the development of cybersecurity. It proposes a security framework to deal with security challenges in Web3.
KeXin Gong, Xiangmei Song, Na Wang, Chunyang Wang · 5 authors
Abstract The security of smart contract has always been one of the significant problems in blockchain. As shown in previous studies, vulnerabilities in smart contracts can lead to unpredictable losses. With the rapid growth of the number of smart contracts, more and more data driven detection technologies based on machine learning have been proposed. However, some state‐of‐the‐art approaches mainly rely on the source code of smart contract. These methods are limited by the openness of the source code and the version of the programming language. To address this problem, we propose a novel vulnerability detection method based on transformer by constructing the control flow graph (CFG) of smart contracts operation codes (opcodes), which shields the difference of various versions of program language. Extensive experiments are conducted to evaluate the effectiveness of the proposed method on the authors' own collected dataset. The experimental results show that the proposed method achieves 94.36% accuracy in vulnerability detection, which performs better than other state‐of‐the‐art methods.
Fake news and misinformation are prevalent on the Internet in this day and age. The popularity of social media such as Facebook, Instagram, TikTok has encouraged the people to share news or information over Internet without knowing whether it is a truth or fake information. The outbreak of COVID-19 affected the social activities of all levels of society as people were asked to stay at home to self-quarantine. It indirectly encourages the growth of the social activities online. Even though COVID- 19 is no longer a big threat to the world, people already used to rely on the Internet for the daily activities. Therefore, the trustworthy of the information on the Internet is getting crucial. ETHERST is a blockchain- based PKI that implemented rewarding and punishment mechanism using Ethereum ECR-20 token named PKIToken to improve the trustworthiness of information published by the blockchain nodes. In this paper, we implement an Ethereum-based distributed application (dapp) that allowed the community members to act on trusting and untrusting on information provided by any of the members. With the ETHERST framework as the backend, the ETHERSTWEB is equipped with the rewarding and punishment mechanism to keep the community from misusing the trusting and untrusting action to maintain the trustworthiness of information of a member. With the PKIToken amount level implemented in the backend, it provides an index to the trustworthiness of a member in the community. It has the advantages over the existing rating or review systems that are commonly implemented in many traditional web applications.
Cryptocurrencies are rapidly expanding and becoming vital in digital financial markets. However, the rise in cryptocurrency-related illicit activities has led to significant losses for users. To protect the security of these platforms, it is critical to identify illicit accounts effectively. Current detection methods mainly depend on feature engineering or are inadequate to leverage the complex information within cryptocurrency transaction networks, resulting in suboptimal performance. In this paper, we present DIAM, an effective method for detecting illicit accounts in cryptocurrency transaction networks modeled by directed multi-graphs with attributed edges. DIAM first features an Edge2Seq module that captures intrinsic transaction patterns from parallel edges by considering edge attributes and their directed sequences, to generate effective node representations. Then in DIAM, we design a multigraph Discrepancy (MGD) module with a tailored message passing mechanism to capture the discrepant features between normal and illicit nodes over the multigraph topology, assisted by an attention mechanism. DIAM integrates these techniques for end-to-end training to detect illicit accounts from legitimate ones. Extensive experiments, comparing against 15 existing solutions on 4 large cryptocurrency datasets of Bitcoin and Ethereum, demonstrate that DIAM consistently outperforms others in accurately identifying illicit accounts. For example, on a Bitcoin dataset with 20 million nodes and 203 million edges, DIAM attains an F1 score of 96.55%, markedly surpassing the runner-up's score of 83.92%. The code is available at https://github.com/TommyDzh/DIAM.
The Ponzi scheme, an old-fashioned fraud, is now popular on the Ethereum blockchain, causing considerable financial losses to many crypto investors. A few Ponzi detection methods have been proposed in the literature, most of which detect a Ponzi scheme based on its smart contract source code. This contract-code-based approach, while achieving very high accuracy, is not robust because a Ponzi developer can fool a detection model by obfuscating the opcode or inventing a new profit distribution logic that cannot be detected. On the contrary, a transaction-based approach could improve the robustness of detection because transactions, unlike smart contracts, are harder to be manipulated. However, the current transaction-based detection models achieve fairly low accuracy. In this paper, we aim to improve the accuracy of the transaction-based models by employing time-series features, which turn out to be crucial in capturing the life-time behaviour a Ponzi application but were completely overlooked in previous works. We propose a new set of 85 features (22 known account-based and 63 new time-series features), which allows off-the-shelf machine learning algorithms to achieve up to 30% higher F1-scores compared to existing works.
Communication using Emails, SMS, and various social media platforms have become an important part of life when dealing professionally and socially. Due to their large uses, these platforms also have gained the attention of hackers to carry out sophisticated attacks by sending out messages that contains Malicious content (Generally URL). Huge numbers of Phishing emails are sent daily. Over the past few years, various Machine Learning based techniques were introduced to identify Phishing Attacks still, the count and loss due to Phishing is increasing daily. Blockchain technology is gaining a lot of attention in Security Domain over the past few years, in this state of art authors have proposed a blockchain-based system integrated with a Machine Learning model to identify and prevent Phishing content that is sent out on various messaging platforms. For implementation purposes Ethereum Based platform and from a Machine Learning perspective Classification based Gradient Boost Algorithm and Support Vector Machine Algorithm was used. The proposed systems talk about, sender while sending out a message to a recipient should pay some ETH (cryptocurrency) and if after content validation through ML models the message is found to be legitimate, the ETH value that the sender had paid will be refunded back, else if ML models identify the content as Phishing, then there will be no refund. Even though after validation through the ML model if the recipient marks the email as SPAM or reports the same as Suspicious then also there will be no refund. This eventually will reduce the traffic and will make hackers rethink when sending Phishing Messages. Authors were able to Create a PoC illustrating the same. API endpoints that were created in this state-of-art executed within 1000 ms & the accuracy obtained from the Machine Learning model was also high.
Validating an applicant's credentials and expertise prior to hiring is one of the most elementary yet crucial responsibilities for every company. However, it is extremely time-consuming owing to the soaring number of applicants, especially in larger firms. Therefore, it is overlooked many times. The hiring department is increasingly concerned about the applicants providing incorrect information, and while traditional talent verification tools are helpful, they are still far from ideal for handling it. Although expensive, this activity is crucial, thus it needs to be made more efficient and cost-effective. Blockchain is a new technology that, due to its decentralised and distributed ledger system, ensures security and trust. Although this is a high-cost activity it is very significant, and hence, needs to be made more efficient and economical. Blockchain is an emerging technology that guarantees security and trust due to its decentralised and distributed ledger mechanism. Therefore, a blockchain based system for the verification of candidates credentials is a promising solution. Furthermore, from an applicant's point of view, it can become overwhelming to pick a job role in the technology industry considering the wide array of career opportunities and roles that are available today. Hence, a sophisticated machine learning algorithm can be used to recommend job titles to student applicants to help ease their decision-making process and provide them with necessary input concerning any career decisions that they would want to make in the future.
Blockchain has facilitated the emergence of automation and decentralization concepts, leading to significant organizational and operational changes in businesses, e.g., decentralized autonomous organizations (DAOs). In DAOs, management decisions are made collectively and automatically through smart contracts without a central authority, which results in increased cybersecurity requirements. While blockchain integration aims to eliminate single points of failure and enhance data integrity, DAOs remain susceptible to vulnerabilities in consensus mechanisms, key management, and software management, highlighting the need for intrusion detection. Collaborative intrusion detection has been identified as a potential solution to address emerging cyberattacks in a decentralized environment; however, it is not yet fully developed. This study proposes a federated adaptive neuro-fuzzy inference system (FANFIS) for collaborative intrusion detection in blockchain–Internet-of-Things (IoT) networks. The FANFIS maintains a global intrusion detection model in a privacy-preserving manner over the network. Through computational experiments with datasets of KDDCUP99 and Bot-IoT, we found that using the FANFIS reduced the computational time for model training by an average of 49.42% while maintaining a high-performance level. The superior performance of the FANFIS, as demonstrated by its accuracy, precision, and F1-score, surpasses the conventional method involving data centralization, exhibiting mean percentage errors of 1.4092%, 2.6935%, and 1.3463%, respectively.