Deep Learning-Based Malicious Smart Contract and Intrusion Detection System for IoT Environment

Abstract

The Internet of Things (IoT) is a key enabler technology that recently received significant attention from the scientific community across the globe. It helps transform everyone’s life by connecting physical and virtual devices with each other to offer staggering benefits, such as automation and control, higher productivity, real-time information access, and improved efficiency. However, IoT devices and their accumulated data are susceptible to various security threats and vulnerabilities, such as data integrity, denial-of-service, interception, and information disclosure attacks. In recent years, the IoT with blockchain technology has seen rapid growth, where smart contracts play an essential role in validating IoT data. However, these smart contracts can be vulnerable and degrade the performance of IoT applications. Hence, besides offering indispensable features to ease human lives, there is also a need to confront IoT environment security attacks, especially data integrity attacks. Toward this aim, this paper proposed an artificial intelligence-based system model with a dual objective. It first detects the malicious user trying to compromise the IoT environment using a binary classification problem. Further, blockchain technology is utilized to offer tamper-proof storage to store non-malicious IoT data. However, a malicious user can exploit the blockchain-based smart contract to deteriorate the performance IoT environment. For that, this paper utilizes deep learning algorithms to classify malicious and non-malicious smart contracts. The proposed system model offers an end-to-end security pipeline through which the IoT data are disseminated to the recipient. Lastly, the proposed system model is evaluated by considering different assessment measures that comprise the training accuracy, training loss, classification measures (precision, recall, and F1 score), and receiver operating characteristic (ROC) curve.

Malicious Contract Detection for Blockchain Network Using Lightweight Deep Learning Implemented through Explainable AI

“…In [5], the authors proposed a system that detects malicious contracts after first detecting malicious users. This is the latest work in the field of malicious smart contract detection.…”

“…For the well-known MAIAN tool, various detection methods have been proposed. In previous work [5], the latest deep learning-based detection technique is described, which can also detect malicious contracts, but the number of datasets used is very small. Therefore, the reliability is not high, and it is difficult to state that it is robust.…”

“…There are two main ways to detect malicious activity: malicious node detection and malicious smart contract detection. Among the latter, various malicious smart contract detection models have been proposed [5][6][7] to detect malicious smart contracts. Most deep-learningbased methods detect malicious smart contracts by learning the features of smart contracts.…”

ROAST-IoT: A Novel Range-Optimized Attention Convolutional Scattered Technique for Intrusion Detection in IoT Networks

“…Nevertheless, incorporating physical items with the Internet exposes most of our regular activities to security risks [6,7]. When different types of devices are connected to a network, it is clear that the simple availability of these resources raises IoT, which in turn helps new applications grow in popularity.…”

“…With the decline in sensor prices, the rise of remote storage services, and the popularity of big data, the IoT is seen as a viable solution to raise people's quality of life. Nevertheless, incorporating physical items with the Internet exposes most of our regular activities to security risks [6,7]. When different types of devices are connected to a network, it is clear that the simple availability of these resources raises IoT, which in turn helps new applications grow in popularity.…”