This paper presents the design, development, and thorough evaluation of a novel network security prototype that integrates Artificial Intelligence (AI) and blockchain technology to significantly enhance cyber security. As AI becomes increasingly embedded in cybersecurity solutions, ensuring the provenance, accountability, and integrity of AI-generated decisions has emerged as a critical challenge. Without reliable logging mechanisms, AI models remain vulnerable to adversarial manipulation and pose significant risks to critical security infrastructure. To address this, our research combines a state-of-the-art Convolutional Neural Network (CNN)-based threat detection module with a permissioned Ethereum-compatible blockchain. A custom-designed Solidity smart contract ensures secure, structured storage of comprehensive AI model metadata, while interactions with the blockchain are seamlessly managed through a lightweight Flask-based REST API. Each recorded transaction generates a unique cryptographic fingerprint, providing robust evidence for audits and forensic analyses. We evaluated the system's effectiveness through rigorous experimentation on a controlled test network, confirming immutability, traceability, and verifiable integrity of all logged metadata entries. Results demonstrated significant improvements in anomaly detection accuracy, reduced false-positive rates, and ensured real-time responsiveness essential for effective intrusion prevention. Despite controlled-environment limitations, such as transaction latency and blockchain-related operational costs, our prototype successfully establishes proof-of-concept for leveraging blockchain as an immutable audit trail for AI-driven cybersecurity systems. Future research directions include integrating advanced scaling techniques, such as layer 2 solutions, and extending the blockchain logging capabilities to cover the entire AI model lifecycle, including detailed training logs and comprehensive version histories. This work provides foundational contributions towards building trusted, auditable, and transparent AI solutions in regulated cyber security domains.
The rapid adoption of Internet of Things (IoT) devices has significantly increased cybersecurity risks, making them vulnerable to anomalies, attacks, and unauthorized access. Traditional security mechanisms struggle to handle the massive data flow, real-time processing requirements, and evolving cyber threats in IoT networks. This paper presents an integrated approach using Deep Neural Networks and Blockchain technology (DNNs-BCT) to enhance anomaly detection and prevention in IoT environments. Our proposed framework employs DNNs for intelligent anomaly detection, leveraging multi-layer feature extraction and adaptive learning mechanisms. The DNN model is trained on IoT traffic datasets to classify network behavior as normal or anomalous, effectively detecting threats such as Distributed Denial of Service (DDoS) attacks, malware injections, and insider threats. Unlike traditional rule-based intrusion detection systems (IDS), the DNN continuously learns and adapts to new attack patterns, improving detection accuracy and false-positive reduction. This study integrates Blockchain technology into the IoT ecosystem to ensure data integrity, transparency, and decentralized security. Each IoT device logs its activity onto a private blockchain network, preventing data tampering, unauthorized access, and single points of failure. The blockchain employs smart contracts for automated threat response, instantly mitigating malicious activity without human intervention. This distributed ledger approach enhances trust, authentication, and secure communication across IoT devices. The synergy between DNN-based anomaly detection and Blockchain-based security provides a robust, scalable, and adaptive solution for real-time cybersecurity threats in IoT networks. With a low false-positive rate of 15.42% and a strong detection accuracy of 99.18%, the proposed model successfully identifies malicious activity, including malware injections and Distributed Denial of Service (DDoS) assaults. Blockchain technology replaces single points of failure and forbids illegal changes by providing data integrity, openness, and decentralizing powers. Furthermore, smart contracts allow autonomous, real-time attack responses, enhancing reaction time efficiency (95.25%) and general system scalability (94.96%).
Blockchain technology has transformed how data are stored and transactions are processed in a distributed environment. Blockchain assures data integrity by validating transactions through the consensus of a distributed ledger involving several miners as validators. Although blockchain provides multiple advantages, it has also been subject to some malicious attacks, such as a 51% attack, which is considered a potential risk to data integrity. These attacks can be detected by analyzing the anomalous node behavior of miner nodes in the network, and data analysis plays a vital role in detecting and overcoming these attacks to make a secure blockchain. Integrating machine learning algorithms with blockchain has become a significant approach to detecting anomalies such as a 51% attack and double spending. This study comprehensively analyzes various machine learning (ML) methods to detect anomalies in blockchain networks. It presents a Systematic Literature Review (SLR) and a classification to explore the integration of blockchain and ML for anomaly detection in blockchain networks. We implemented Random Forest, AdaBoost, XGBoost, K-means, and Isolation Forest ML models to evaluate their performance in detecting Blockchain anomalies, such as a 51% attack. Additionally, we identified future research directions, including challenges related to scalability, network latency, imbalanced datasets, the dynamic nature of anomalies, and the lack of standardization in blockchain protocols. This study acts as a benchmark for additional research on how ML algorithms identify anomalies in blockchain technology and aids ongoing studies in this rapidly evolving field.
Ye Tian, Liangliang Song, Peng Qian, Yanbin Wang · 6 authors
The detection of malicious accounts on Ethereum - the preeminent DeFi platform - is critical for protecting digital assets and maintaining trust in decentralized finance. Recent advances highlight that temporal transaction evolution reveals more attack signatures than static graphs. However, current methods either fail to model continuous transaction dynamics or incur high computational costs that limit scalability to large-scale transaction networks. Furthermore, current methods fail to consider two higher-order behavioral fingerprints: (1) direction in temporal transaction flows, which encodes money movement trajectories, and (2) account clustering, which reveals coordinated behavior of organized malicious collectives. To address these challenges, we propose DiT-SGCR, an unsupervised graph encoder for malicious account detection. Specifically, DiT-SGCR employs directional temporal aggregation to capture dynamic account interactions, then coupled with differentiable clustering and graph Laplacian regularization to generate high-quality, low-dimensional embeddings. Our approach simultaneously encodes directional temporal dynamics, global topology, and cluster-specific behavioral patterns, thereby enhancing the discriminability and robustness of account representations. Furthermore, DiT-SGCR bypasses conventional graph propagation mechanisms, yielding significant scalability advantages. Extensive experiments on three datasets demonstrate that DiT-SGCR consistently outperforms state-of-the-art methods across all benchmarks, achieving F1-score improvements ranging from 3.62% to 10.83%.
This study introduces an enhanced anomaly detection framework integrating Time-[Formula: see text]-Variational Autoencoders (Time-[Formula: see text]-VAE) and Transformer architectures for blockchain-based carbon trading markets. Against intensifying global climate challenges, ensuring carbon market integrity is critical. While blockchain technology enhances transparency, it simultaneously introduces novel regulatory complexities in detecting sophisticated anomalies. Our improved hybrid model, trained on raw transaction records of Moss Carbon Credit (MCO2) tokens sourced via Ethereum blockchain APIs, demonstrates significant efficacy in identifying critical anomalies including smart contract-driven token distribution and fake liquidity attacks through empirical case analysis. The research establishes a scientific framework for blockchain deployment and supervision in carbon markets.
The exponential growth in power consumption demands a robust method to address and identify irregularities in distribution systems. This paper presents a novel approach integrating advanced machine learning with blockchain technology to enhance microgrid energy systems' anomaly detection and response times. The Isolation Forest algorithm is employed to identify outliers in power consumption. Custom statistical methods, such as Sudden Change Detection and Z-score, detect abrupt changes in power consumption patterns and statistical anomalies. To ensure prompt and automatic responses to identified irregularities, smart contracts are deployed on the Ethereum platform, enabling the instantaneous implementation of corrective measures. The system's real-time capabilities are enabled by the Web3 library, which establishes a direct connection between anomaly detection algorithms and smart contract execution, making the solution viable for practical deployment. The proposed model is demonstrated using a microgrid power consumption dataset, highlighting how smart contracts enable real-time detection and notification of anomalies. Upon identifying irregular power consumption, the smart contract recommends corrective actions, such as initiating load shedding and ensuring timely and transparent intervention. This integration of blockchain technology enhances the accuracy and efficiency of anomaly detection and provides a decentralized and autonomous solution for alerting system operators, reinforcing the security and reliability of microgrid energy systems.
Autonomous Vehicles (AV) proliferation brings important and pressing security and reliability issues that must be dealt with to guarantee public safety and help their widespread adoption. The contribution of the proposed research is towards achieving more secure, reliable, and trustworthy autonomous transportation system by providing more capabilities for anomaly detection, data provenance, and real-time response in safety critical AV deployments. In this research, we develop a new framework that combines the power of Artificial Intelligence (AI) for real-time anomaly detection with blockchain technology to detect and prevent any malicious activity including sensor failures in AVs. Through Long Short-Term Memory (LSTM) networks, our approach continually monitors associated multi-sensor data streams to detect anomalous patterns that may represent cyberattacks as well as hardware malfunctions. Further, this framework employs a decentralized platform for securely storing sensor data and anomaly alerts in a blockchain ledger for data incorruptibility and authenticity, while offering transparent forensic features. Moreover, immediate automated response mechanisms are deployed using smart contracts when anomalies are found. This makes the AV system more resilient to attacks from both cyberspace and hardware component failure. Besides, we identify potential challenges of scalability in handling high frequency sensor data, computational constraint in resource constrained environment, and of distributed data storage in terms of privacy.
Abstract 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.
Jinish Patel, Joseph Reiner, Brenden Stilwell, Abdullah Wahbeh · 5 authors
With the growing popularity of cryptocurrencies, detecting potential market manipulation and fraudulent activities has become crucial for maintaining market integrity. In this study, we aim to detect anomalous Bitcoin transactions using an integrated approach by combining clustering techniques with statistical outlier detection. More specifically, anomalies were detected using three approaches: a distance-based method, flagging points with distances greater than the 95th percentile from their cluster centers; a statistical method, identifying transactions with any feature having an absolute Z-score greater than 3; and a hybrid approach, where transactions flagged by either method were considered anomalous. Using sample subset Bitcoin transaction data from 2015, our results showed that the combined approach was able to achieve the best performance with a total of 6492 (6.61%) detected anomalous transactions out of a total of 98,151 transactions.
Sarthak Nimje, Rushab Taneja, Om Baviskar, Rachana Patil
Educational institutions face significant challenges with event attendance verification, including manual document validation, fraud risks, and delayed approval processes. This study introduces ElizaEdu, a novel decentralized AI agent system utilizing Ethereum blockchain and ElizaOS to automate and secure attendance verification workflows for academic events. The proposed system integrates autonomous AI agents to handle document validation, approval processes, and ERP integration, while utilizing blockchain technology for immutable record-keeping. The system employs four specialized agents: RequestBot for initial verification, VerifyBot for teacher validation, ApproveBot for department head confirmation, and ERPBot for automatic attendance updates. Through a 3-month pilot implementation with 120 students and 15 faculty members, ElizaEdu demonstrated an 85% reduction in verification time, complete elimination of document fraud, and 84% decrease in administrative workload. The system achieves 97.3% accuracy in document validation and 100% data integrity through blockchain verification. This study presents the architecture, implementation details, and evaluation results, demonstrating ElizaEdu’s effectiveness in transforming attendance management in educational institutions.
In recent years, a large number of on-chain attacks have emerged in the blockchain empowered Web3 ecosystem. In the year of 2023 alone, on-chain attacks have caused losses of over 585 million. Attackers use blockchain transactions to carry out on-chain attacks, for example, exploiting vulnerabilities or business logic flaws in Web3 applications. A wealth of efforts have been devoted to detecting on-chain attack transactions through expert patterns and machine learning techniques. However, in this ever-evolving ecosystem, the performance of current methods is limited in detecting new on-chain attacks, due to the obsoleting of attack recognition patterns or the reliance on on-chain attack samples. In this paper, we propose a universal approach for detecting on-chain attacks even when there are few or even no new on-chain attack samples. Specifically, an in-depth analysis of the transaction characteristics is conducted, and we propose a new insight to train a generic attack transaction detecting model, i.e., transaction reconstruction. Particularly, to overcome the over-fitting in the transaction reconstruction task, we use the web-scale function comments related to transactions as supervision information, rather than expert-confirmed labels. Experimental results demonstrate that the proposed approach surpasses the supervised state-of-the-art by 13% in AUC, with just 30 known on-chain attack samples. Moreover, without any known attack samples, our method can still detect new on-chain attacks in the wild (with a precision of 61.83%). Among attacks detected in the wild, we confirm 1,692 address poisoning attacks, a new type of on-chain attack targeting token holders. Our code is available at: https://github.com/wuzhy1ng/attack_trans_detection_www25.
Muhammad Kamran, Maaz Rehan, Muhammad Maaz Rehan, Wasif Nisar · 6 authors
Blockchain technology is increasingly being adopted across critical domains, such as healthcare and finance, yet it remains susceptible to anomalies and malicious attacks. Hence, robust anomaly detection is essential in these decentralized systems to maintain integrity, trust, and reliability. However, anomaly detection is still challenging due to data imbalances, adversarial resilience, and the lack of explanation in existing approaches. This work presents ARCADE, a novel approach for adversarially resilient anomaly detection in blockchain networks that leverages an optimized cost-sensitive stacking ensemble learning combined with explainable artificial intelligence (XAI) techniques. Firstly, the proposed approach uses cost-sensitive learning to address the data imbalance problem by optimizing class weights that are integrated with stacking ensemble learning to enhance detection accuracy. Secondly, along with this, newly engineered features are employed to strengthen the resilience of the model against malicious perturbations. Lastly, XAI techniques are applied to provide comprehensive insights and explanations for model prediction. To evaluate ARCADE, the Ethereum network transactions dataset is utilized to ensure a realistic case study. The experimental results show the superiority of the ARCADE in several aspects, achieving a high accuracy of 99.65%; strong resilience against adversarial perturbations, achieving an accuracy of 99.38% for low-intensity attacks, 91.04% for moderate attacks, and over 78% for extreme attacks; and surpassing existing techniques while also providing explainability for domain users.
Zaid Alsalami, L. Chandra Sekhar Reddy, Kambhampati Saritha, I. B. Ranitha · 6 authors
Spatio temporal learning from scratch is a revolution that allows AI generated synthetic intelligence systems to learn tasks without any previous training to the task itself. This work presents a novel combination of transformer-encoded and membrane augmented domain adaptor frame that enables the AI systems to generalize over domains at run time. Unlike existing conventional AI models that require large amounts of labeled dataset, our work addresses this problem through the use of: self-supervised meta learning, multi modal data fusion, neuro symbol representation in order to extract spatial and temporal patterns in a dataset arising from multiple data sources. Moreover, the proposed system also comprises federated learning with decentralized knowledge graphs secured by blockchain technology for ensuring private transfer of AI knowledge among different organizations. Multiple real world applications created for autonomous systems, climate prediction, smart healthcare and industrial digital twins are evaluated against the framework in which the best performance is achieved on zero shot applications. The results from the experiment demonstrate how the system can reason, interpret, and makes accurate predictions in unseen domains and still be very computationally efficient. Symbolic logic integration provides an additional aspect for explainability, while further improving the understanding of the AI decisions. By bridging the gap between zero shot learning, spatio-temporal modeling, and decentralized Artificial Intelligence, and by ensuring adaptable, efficient, and privacy considering artificial intelligence, this research paves the way for next generation of synthetic intelligence. This leads us to future directions of scaling the framework to high dimension and making the task more real time adaptable.
Blockchain networks have become a cornerstone of decentralized finance and digital asset management, yet they remain susceptible to fraudulent activities, money laundering, and illicit financial transactions. Traditional anomaly detection methods, including rule-based systems and supervised machine learning models, often struggle to generalize across evolving blockchain transaction patterns due to their reliance on static heuristics and manually engineered features. Graph-based learning techniques offer a more robust approach by leveraging the inherent structure of blockchain transactions, where wallets and transactions form a dynamic graph.This study proposes a novel Spatial-Temporal Graph Neural Network (STGNN)-based anomaly detection framework for blockchain transactions. By modeling transaction flows as evolving graphs, the proposed system captures both spatial dependencies between wallets and temporal patterns in transaction sequences. The framework employs Graph Convolutional Networks (GCN) or Graph Attention Networks (GAT) to extract spatial representations, while Gated Recurrent Units (GRU) or Temporal Convolutional Networks (TCN) model the time-dependent evolution of transaction behaviors. The fusion of these spatial-temporal features enables the detection of anomalous transactions that deviate from expected network behaviors.Experimental evaluations on real-world blockchain datasets demonstrate that the STGNN-based model achieves higher detection accuracy, lower false positive rates, and better adaptability than traditional fraud detection techniques. The study further explores the system's scalability and generalization across different blockchain networks, revealing its potential for real-time monitoring of illicit financial activities. These findings highlight the effectiveness of graph-based deep learning models in strengthening blockchain security and provide a foundation for future research in decentralized fraud detection, anti-money laundering (AML) compliance, and intelligent financial surveillance.
The rapid expansion of blockchain technology has led to increased security challenges, particularly in detecting fraudulent transactions and malicious activities within decentralized networks. Traditional anomaly detection techniques, including rule-based heuristics and supervised learning models, struggle to adapt to the dynamic and complex nature of blockchain transactions. This paper introduces a graph neural network (GNN)-based anomaly detection framework designed to improve blockchain security by leveraging the inherent graph structure of transaction networks. The proposed approach models blockchain transactions as a directed graph, where nodes represent wallet addresses and edges correspond to transaction flows. By applying spatial and temporal graph learning techniques, the framework captures both network topology and transaction evolution over time, allowing for the identification of anomalous activities such as money laundering, phishing scams, and Ponzi schemes. The GNN model incorporates graph convolutional networks (GCN), graph attention networks (GAT), and gated recurrent units (GRU) to learn both spatial dependencies and sequential patterns within blockchain transactions. Experiments conducted on Bitcoin and Ethereum transaction datasets demonstrate that the GNN-based framework outperforms conventional fraud detection methods in terms of precision, recall, and false positive reduction. The model successfully detects fraudulent transactions with an F1-score of 0.92, showing its effectiveness in identifying emerging threats in blockchain networks. These results highlight the potential of deep learning-based anomaly detection in enhancing blockchain security, providing a scalable and adaptive solution for detecting fraud in decentralized financial ecosystems.
The identification of vulnerabilities in smart contracts is necessary for ensuring their security. As a pre-trained language model, BERT has been employed in the detection of smart contract vulnerabilities, exhibiting high accuracy in tasks. However, it has certain limitations. Existing methods solely depend on features extracted from the final layer, thereby disregarding the potential contribution of features from other layers. To address these issues, this paper proposes a novel method, which is named multi-layer feature fusion (MULF). Experiments investigate the impact of utilizing features from other layers on performance improvement. To the best of our knowledge, this is the first instance of multi-layer feature sequence fusion in the field of smart contract vulnerability detection. Furthermore, there is a special type of patched contract code that contains vulnerability features which need to be studied. Therefore, to overcome the challenges posed by limited smart contract vulnerability datasets and high false positive rates, we introduce a data augmentation technique that incorporates function feature screening with those special smart contracts into the training set. To date, this method has not been reported in the literature. The experimental results demonstrate that the MULF model significantly enhances the performance of smart contract vulnerability identification compared to other models. The MULF model achieved accuracies of 98.95% for reentrancy vulnerabilities, 96.27% for timestamp dependency vulnerabilities, and 87.40% for overflow vulnerabilities, which are significantly higher than those achieved by existing methods.
Blockchain technology consists of distributed ledgers or database systems, regarded as immutable, secure, and innovative, characterized by unsupervised internal maintenance with a special security protocol used to prevent inference from malicious or third parties. The widespread use of this technology has led to deep research into the problems posed by this technology, which can be summarized in terms of computational cost and latency time. The crime detection process in video surveillance has made great progress with the use of technologies such as the Internet of Things and blockchain technologies. However, to reach high levels of security in the physical crime detection process in which data are sent to servers via a computer network, there must be a high degree of security for Internet of Things systems related to the crime detection process. There has been a significant increase in the number of problems associated with crime detection in video surveillance systems, including the modification of surveillance data during transfer to and from servers. For this reason, establishing a reliable and secure system for transferring video surveillance data to servers has become a high priority. This paper presents a lightweight security system to protect data generated in the crime detection process, both from video surveillance cameras and the servers that store these data. The challenges related to IoT-based video surveillance cameras and monitoring and control centers have been considered, turning the system primarily into a decentralized system. In this paper, a lightweight blockchain system based on a proof of secret share consensus algorithm technology is proposed, along with the encryption of surveillance data via modified Okamoto–Uchiyama homomorphic encryption technology. The proposed system is evaluated via standard blockchain and security evaluation metrics, demonstrating efficient utilization of computational costs and realization of security, with a high scalability rate. The VGG16 deep learning model is employed in the proposed system to detect and classify criminal activities in surveillance videos. Owing to its ability to identify patterns and anomalies, the model achieved an accuracy of 94%, demonstrating a high level of performance in crime detection and prevention. Overall, the use of VGG16 provides an efficient and reliable approach for improving the security of public spaces and reducing the risk of criminal activity.
Shiyang Chen, Yang Liu, Qun Zhang, Z. Shao · 5 authors
This article presents MDST‐GNN, a multi‐distance spatial‐temporal graph neural network for blockchain anomaly detection. To address challenges in detecting fraudulent cryptocurrency transactions, MDST‐GNN integrates a multi‐distance graph convolutional architecture with adaptive temporal modeling, enabling capture of both local and global spatial dependencies while inferring patterns from anonymized temporal data. The model incorporates self‐supervised learning to enhance generalization ability. Experiments on the Elliptic dataset demonstrate MDST‐GNN's superior performance over state‐of‐the‐art methods, achieving improvements of 1.5% in AUC‐ROC and 2.9% in AUC‐PR. The model's robustness to temporal granularity and effectiveness in identifying suspicious transactions underscore its practical value for blockchain forensics.
Bianka Bosnyaková, František Babič, Tomáš Adam, Anna Biceková
Blockchain technology is gaining popularity and is widely used in cryptocurrencies, NFTs, and the financial sector. With the increasing number of transactions and the expansion of blockchain networks, a higher risk of fraudulent activities occurs, which is difficult to monitor and detect manually. Therefore, anomaly detection in blockchain data becomes an important approach for identifying suspicious activities, system errors, or other unusual behaviors. This article deals with the application of data analytics methods to the detection of anomalies in transaction data of the WAX Blockchain network, with a focus on NFT sales. In our research, we implemented a method for tracking NFT sales, focusing on identifying significant price deviations as potential indicators of suspicious activity. This method assumes that while the market value of NFTs can fluctuate, a transaction with a significantly higher price than usual may signal potential money laundering, market manipulation, or other illicit activities.
Blockchains are the backbone behind cryptocurrency networks, which have developed rapidly in the last two decades. However, this growth has brought several challenges due to the features of these networks, specifically anonymity and decentralization. One of these challenges is the fight against fraudulent activities performed in these networks, which, among other things, involve financial schemes, phishing attacks or money laundering. This article will address the problem of identifying fraud cases among a large set of transactions extracted from the Bitcoin network. More specifically, our study’s goal was to find reliable techniques to label Bitcoin transactions, taking into account their features. The approach followed involved two kinds of Machine Learning methods. On the one hand, anomaly detection algorithms were applied to determine whether fraudulent activities tend to show anomalous behaviour without resorting to manually obtained labels. On the other hand, Heterogeneous Graph Transformers were used to leverage the heterogeneous relational nature of the cryptocurrency information. As a result, the article will provide reasonable conclusions to acknowledge that unsupervised approaches can be useful for fraud detection on blockchain networks. Furthermore, the effectiveness of supervised graph methods was revalidated, emphasizing the importance of data heterogeneity.