arrow
返回

Malware Speaks! Deep Learning Based Assembly Code Processing for Detecting Evasive Cryptojacking

delete2024-07-01
delete0
PRE
AI
G
Ganapathy Mani *
M
Myeongsu Kim
B
Bharat Bhargava
P
Pelin Angın
A
Ayça Deniz
V
Vikram Pasumarti
DOI:10.1109/TDSC.2023.3307445delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
The increasing prevalence of blockchain-based cryptocurrencies as a payment instrument in the past decade and the rewards earned by the cryptominers has resulted in a new class of cyber attacks, cryptojacking, which involves unauthorized mining of cryptocurrencies on someone's system. Spotting cryptojacking is difficult in many cases, since the relevant software tries to disguise its presence to evade detection, by mimicking benign software such as compression applications by performing similar bitwise, cryptographic, and encryption operations. In this paper, we propose the processing of assembly code-a fundamental and platform-independent programming language-as a natural language using deep learning for profiling applications, which we call Deep Code Profiler (DeCode Pro). Our proposed solution leverages the immutable step of any cyber attack: the deployment of instructions in system memory to carry out the attack. Through extensive experimentation with different neural network architectures in the profiling stage, we show that DeCode Pro is highly effective in the detection of evasive cryptojacking attacks and achieves low false positive and false negative rates. We also show that the model achieves high classification accuracy even with limited training data, which can considerably reduce the computing resources required for training and retraining the deep learning model.
Keyword:
Deep learning
Malware
Cyberattack
Codes
Feature extraction
Blockchains
Natural language processing
Assembly code
cryptojacking
cryptomining
deep learning
LSTM
natural language processing

期刊

IEEE Transactions on Dependable and Secure Computing 封面图
IEEE Transactions on Dependable and Secure Computing
IF:
7.5
论文数:
2.6K
被引数:
9.6K

机构

Purdue University System 封面图
Purdue University System
学者数:
4.0W
论文数: 3.6W
被引数: 66
P
Purdue University
学者数:
2.7W
论文数: 2.1W
被引数: 147
引用论文

引用论文

err分享
err收藏
err分享
err收藏
Detecting Cryptomining Malware: a Deep Learning Approach for Static and Dynamic Analysis
err2020-01-21
err66
PREAI
errDarabian, Hamid; Homayounoot, Sajad; Dehghantanha, Ali; Hashemi, Sattar; Karimipour, Hadis; Parizi, Reza M.; Choo, Kim-Kwang Raymond
err分享
err收藏
Machine Health Monitoring Using Local Feature-Based Gated Recurrent Unit Networks
err2018-02-01
err636
PREAI
errZhao, Rui; Wang, Dongzhe; Yan, Ruqiang; Mao, Kezhi; Shen, Fei; Wang, Jinjiang
err分享
err收藏
学者 查看更多内容