A hybrid model of Lightgbm and xDeepFM for the prediction of malware infection

Xiao Xiong; Yeming Cai; Guanghui Gao; Chenglong Song

doi:10.1117/12.3004711

11 October 2023 A hybrid model of Lightgbm and xDeepFM for the prediction of malware infection

Xiao Xiong, Yeming Cai, Guanghui Gao, Chenglong Song

Proceedings Volume 12800, Sixth International Conference on Computer Information Science and Application Technology (CISAT 2023); 128006S (2023) https://doi.org/10.1117/12.3004711
Event: 6th International Conference on Computer Information Science and Application Technology (CISAT 2023), 2023, Hangzhou, China

Abstract

With the rapid development of networking, the uncontrolled spread and infection of malware has caused great troubles on the Internet, and even caused serious damage to people's interests. Using machine learning algorithms and big data, Using machine learning algorithms and big data, it is of great significance to predict the computers that may be infected with malware and send out a warning. In this paper, using the malware data set provided by Microsoft, a hybrid model based on xDeepFM and LightGBM algorithm is constructed to predict the probability of computer infection. In the second section, the related work and current research progress are investigated, and the third and fourth sections respectively introduce our algorithms, hybrid model and experimental flow. In order to quantitatively evaluate the performance of our model, AUC is selected as the evaluation index and compared with other machine learning algorithms. The experimental results show that our hybrid model has the highest AUC value of 0.698, which is 0.009, 0.023 and 0.007 higher than xDeepFM, Xgboost and LightGBM models, respectively.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Xiao Xiong, Yeming Cai, Guanghui Gao, and Chenglong Song "A hybrid model of Lightgbm and xDeepFM for the prediction of malware infection", Proc. SPIE 12800, Sixth International Conference on Computer Information Science and Application Technology (CISAT 2023), 128006S (11 October 2023); https://doi.org/10.1117/12.3004711

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available