Blockchain-enabled fraud discovery through abnormal smart contract detection on Ethereum

Liu, Lin; Tsai, Wei‐Tek; Bhuiyan, Md. Zakirul Alam; Peng, Hao; Liu, Mingsheng

doi:10.1016/j.future.2021.08.023

Cited by 77 publications

(25 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning has lately emerged as a popular issue in the field of machine learning. Deep learning techniques include convolutional networks, deep belief networks, and deep autoencoders, which are hierarchical learning structures with several layers of input processing for representation learning or pattern classification [20][21][22]. Deep learning may be traced back to the study of artificial neural networks.…”

Section: Proposed Modelmentioning

confidence: 99%

Modified Genetic Algorithm with Deep Learning for Fraud Transactions of Ethereum Smart Contract

et al. 2023

View full text Add to dashboard Cite

Recently, the Ethereum smart contracts have seen a surge in interest from the scientific community and new commercial uses. However, as online trade expands, other fraudulent practices—including phishing, bribery, and money laundering—emerge as significant challenges to trade security. This study is useful for reliably detecting fraudulent transactions; this work developed a deep learning model using a unique metaheuristic optimization strategy. The new optimization method to overcome the challenges, Optimized Genetic Algorithm-Cuckoo Search (GA-CS), is combined with deep learning. In this research, a Genetic Algorithm (GA) is used in the phase of exploration in the Cuckoo Search (CS) technique to address a deficiency in CS. A comprehensive experiment was conducted to appraise the efficiency and performance of the suggested strategies compared with those of various popular techniques, such as k-nearest neighbors (KNN), logistic regression (LR), multi-layer perceptron (MLP), XGBoost, light gradient boosting machine (LGBM), random forest (RF), and support vector classification (SVC), in terms of restricted features and we compared their performance and efficiency metrics to the suggested approach in detecting fraudulent behavior on Ethereum. The suggested technique and SVC models outperform the rest of the models, with the highest accuracy, while deep learning with the proposed optimization strategy outperforms the RF model, with slightly higher performance of 99.71% versus 98.33%.

show abstract

Section: Proposed Modelmentioning

confidence: 99%

Modified Genetic Algorithm with Deep Learning for Fraud Transactions of Ethereum Smart Contract

et al. 2023

View full text Add to dashboard Cite

show abstract

“…As a complement to a paragraph of related works on Ponzi scheme detection, a few works proposed approaches to detect frauds in Ethereum. Liu et al [63] presented the smart contract financial fraud as an anomaly detection problem. Based on the code data and transaction data, they succeeded in detecting fraudulent contracts.…”

Section: Fraud Detectionmentioning

confidence: 99%

Applicability of Intrusion Detection System on Ethereum Attacks: A Comprehensive Review

et al. 2022

View full text Add to dashboard Cite

Ethereum attracts more investors, researchers, and even scammers for many reasons; this is the first platform that enables the new Decentralized Applications (DApps) to run on top of the blockchain network. However, the rich semantics and applications of DApps inevitably introduce many security issues that have grabbed significant attention from industry and academics due to their destructive impact on DApps in recent years. Therefore, there is a vital need to study the applicability of Intrusion Detection System in detecting Ethereum-based attacks. Hence, this paper is among the first comprehensive review that studies the applicability of IDS in detecting Ethereum-based attacks. In addition, this paper lists all the potential attacks on Ethereum passing through the vulnerabilities that cause those attacks and ending with the consequences of each attack. Besides, this paper analyses all the IDS-based related works of Ethereum attacks detection since the Ethereum platform was launched in 2015. Finally, this paper discusses the open issues regarding vulnerabilities and attacks, challenges, and future directions.

show abstract

“…Smart contract can sometimes invoke fraudulence, and studies have also shown how to detect those. The study of Liu et al proposes a potential solution to financial fraud on the Ethereum blockchain [33]. In their study, the feature is extracted from complex hierarchical information in smart contracts and these features are represented as a relationship matrix.…”

Section: A Blockchain and Smart Contractmentioning

confidence: 99%

Blockchain and Machine Learning for Fraud Detection: A Privacy-Preserving and Adaptive Incentive Based Approach

et al. 2022

View full text Add to dashboard Cite

Financial fraud cases are on the rise even with the current technological advancements. Due to the lack of inter-organization synergy and because of privacy concerns, authentic financial transaction data is rarely available. On the other hand, data-driven technologies like machine learning need authentic data to perform precisely in real-world systems. This study proposes a blockchain and smart contract-based approach to achieve robust Machine Learning (ML) algorithm for e-commerce fraud detection by facilitating interorganizational collaboration. The proposed method uses blockchain to secure the privacy of the data. Smart contract deployed inside the network fully automates the system. An ML model is incrementally upgraded from collaborative data provided by the organizations connected to the blockchain. To incentivize the organizations, we have introduced an incentive mechanism that is adaptive to the difficulty level in updating a model. The organizations receive incentives based on the difficulty faced in updating the ML model. A mining criterion has been proposed to mine the block efficiently. And finally, the blockchain network is tested under different difficulty levels and under different volumes of data to test its efficiency. The model achieved 98.93% testing accuracy and 98.22% Fbeta score (recall-biased f measure) over eight incremental updates.Our experiment shows that both data volume and difficulty level of blockchain impacts the mining time. For difficulty level less than five, mining time and difficulty level has a positive correlation. For difficulty level two and three, less than a second is required to mine a block in our system. Difficulty level five poses much more difficulties to mine the blocks.INDEX TERMS blockchain, collaborative machine learning, incremental learning, privacy, smart contract Dr. RASHEDUR M. RAHMAN works as a Professor in the Electrical and Computer Engineering Department

show abstract

Blockchain-enabled fraud discovery through abnormal smart contract detection on Ethereum

Cited by 77 publications

References 17 publications

Modified Genetic Algorithm with Deep Learning for Fraud Transactions of Ethereum Smart Contract

Modified Genetic Algorithm with Deep Learning for Fraud Transactions of Ethereum Smart Contract

Applicability of Intrusion Detection System on Ethereum Attacks: A Comprehensive Review

Blockchain and Machine Learning for Fraud Detection: A Privacy-Preserving and Adaptive Incentive Based Approach

Contact Info

Product

Resources

About