
Copyright and License: © The Author(s). The articles are published under the Creative Commons Attribution-ShareAlike 4.0 International License (CC BY-SA 4.0), which permits sharing, adaptation, and reuse with appropriate credit to the original authors and source. Any adapted or derivative work must be distributed under the same CC BY-SA 4.0 license.
Scale-Conjugated Neural Network-Based In-Browser Crypto Jacking Detection through Behavioral Analysis
By: Iqra Aslam | Bilal Shabbir Qaisar | Mubasher Hussain | M. Mudasar Azeem | Fatima Haq | Nimrah Shafiq | Maham Ali
| Pages: 6 - 17
|
Open
Abstract
With the rapid advancements in the field of information technology and computing, the world is moving towards the digital currency called cryptocurrency. Cryptocurrency is actually a way to generate revenue digitally without transferring physical money. The process to generate a coin of cryptocurrency is called blockchain. Crypto mining is not an ethical issue if someone uses legitimate means, but it becomes a cybercrime when others' devices are used unethically. It is because to mine cryptocurrency, very high computational power is required, which leads to a new form of parasitic computing called cryptojacking. In this hacking technique, JavaScript code is embedded into the web pages; when the user visits the malicious websites, one's computer is overloaded to run malicious code without one's consent. The mining leads to consuming battery power and CPU, and raises the electrical bill. The client's device resources are used to mine cryptocurrency for hackers. Cryptojacking is a vast area of research nowadays. This is gaining momentum in the speedy world of the internet. In the last decade, researchers have offered some solutions like browser extensions, static and dynamic analysis. In the proposed model, a systematic approach is given to detect crypto jacking attacks. A scale-conjugated neural network is used to identify browser crypto jacking attacks. It’s done with the help of behavioral analysis by using the parameters CPU utilization, memory, disk read/write, and network interface. Detecting illegal miners is especially useful in a multi-tasking environment where multiple applications run simultaneously.
DOI URL: https://doi.org/10.64820/AEPJMLDL.32.6.17.122026





