@article{ART003317610},
author={Yeeun Lee and Hyeona Jang and Hanseul Jung and Eunjung Choi},
title={Android Malware Classification Using an Edge-Centric Graph Isomorphism Network},
journal={Journal of The Korea Society of Computer and Information},
issn={1598-849X},
year={2026},
volume={31},
number={3},
pages={97-106}
TY - JOUR
AU - Yeeun Lee
AU - Hyeona Jang
AU - Hanseul Jung
AU - Eunjung Choi
TI - Android Malware Classification Using an Edge-Centric Graph Isomorphism Network
JO - Journal of The Korea Society of Computer and Information
PY - 2026
VL - 31
IS - 3
PB - The Korean Society Of Computer And Information
SP - 97
EP - 106
SN - 1598-849X
AB - Function Call Graphs (FCGs) effectively represent execution flows and behavioral structures in static Android malware detection; however, existing studies have shown limitations in utilizing structural edge attribute design by treating function calls as simple connections. This study incorporates diverse edge attributes into Android malware FCGs and comparatively analyzes the performance of GINE (Graph Isomorphism Network with Edge Features)-based malware family classification. Experimental results show that the Baseline model achieved an accuracy of 0.8347 with high variance, whereas Betweenness, ID Distance, and Depth Difference exhibited consistent accuracy improvements of 6.4–7.4 percentage points, and Timestamp, Frequency, and Direction achieved gains of 4.9–5.6 percentage points. These results suggest that structural edge attribute design contributes to improved classification performance and stability in Android malware FCG analysis．
KW - GIN;android;malware;edge feature;cybersecurity;classification
DO -
UR -
ER -
Yeeun Lee, Hyeona Jang, Hanseul Jung and Eunjung Choi. (2026). Android Malware Classification Using an Edge-Centric Graph Isomorphism Network. Journal of The Korea Society of Computer and Information, 31(3), 97-106.
Yeeun Lee, Hyeona Jang, Hanseul Jung and Eunjung Choi. 2026, "Android Malware Classification Using an Edge-Centric Graph Isomorphism Network", Journal of The Korea Society of Computer and Information, vol.31, no.3 pp.97-106.
Yeeun Lee, Hyeona Jang, Hanseul Jung, Eunjung Choi "Android Malware Classification Using an Edge-Centric Graph Isomorphism Network" Journal of The Korea Society of Computer and Information 31.3 pp.97-106 (2026) : 97.
Yeeun Lee, Hyeona Jang, Hanseul Jung, Eunjung Choi. Android Malware Classification Using an Edge-Centric Graph Isomorphism Network. 2026; 31(3), 97-106.
Yeeun Lee, Hyeona Jang, Hanseul Jung and Eunjung Choi. "Android Malware Classification Using an Edge-Centric Graph Isomorphism Network" Journal of The Korea Society of Computer and Information 31, no.3 (2026) : 97-106.
Yeeun Lee; Hyeona Jang; Hanseul Jung; Eunjung Choi. Android Malware Classification Using an Edge-Centric Graph Isomorphism Network. Journal of The Korea Society of Computer and Information, 31(3), 97-106.
Yeeun Lee; Hyeona Jang; Hanseul Jung; Eunjung Choi. Android Malware Classification Using an Edge-Centric Graph Isomorphism Network. Journal of The Korea Society of Computer and Information. 2026; 31(3) 97-106.
Yeeun Lee, Hyeona Jang, Hanseul Jung, Eunjung Choi. Android Malware Classification Using an Edge-Centric Graph Isomorphism Network. 2026; 31(3), 97-106.
Yeeun Lee, Hyeona Jang, Hanseul Jung and Eunjung Choi. "Android Malware Classification Using an Edge-Centric Graph Isomorphism Network" Journal of The Korea Society of Computer and Information 31, no.3 (2026) : 97-106.
