Szczegóły publikacji
Opis bibliograficzny
How powerful are classic Graph Neural Networks for malware detection? : a case study with Cartesian Genetic Programming / Maciej KRZYWDA, Szymon ŁUKASIK, Amir H. Gandomi // W: Progress in Polish artificial intelligence research 6 [Dokument elektroniczny] : 6th Polish Conference on Artifical Intelligence (PP-RAI'2025) : 07–09.04.2025, Katowice, Poland / ed. by Rafał Doroz, Beata Zielosko. — Wersja do Windows. — Dane tekstowe. — Katowice : Wydawnictwo Uniwersytetu Śląskiego, 2025. — e-ISBN: 978-83-226-4405-8. — S. 188–194. — Wymagania systemowe: Adobe Reader. — Bibliogr. s. 193–194, Abstr. — Sz. Łukasik - dod. afiliacja: Systems Research Institute, Polish Academy of Sciences, Warsaw, Poland
Autorzy (3)
- AGHKrzywda Maciej
- AGHŁukasik Szymon
- Gandomi Amir H.
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 165795 |
|---|---|
| Data dodania do BaDAP | 2026-02-04 |
| Tekst źródłowy | URL |
| Rok publikacji | 2025 |
| Typ publikacji | fragment monografii pokonferencyjnej |
| Otwarty dostęp |  |
| Creative Commons | |
| Wydawca | Uniwersytet Śląski w Katowicach |
Abstract
The present study explores an approach to Neural ArchitectureSearch (NAS) using Cartesian Genetic Programming (CGP) for the designand optimization of Graph Neural Networks (GNN) for malware detection.A key aspect of this innovative method is proposing a novel neural architecture. Traditionally, architectures have been manually crafted by humanexperts, which is both time-consuming and prone to errors. In this work,we employ a pure Cartesian Genetic Programming approach (using the 1+λ strategy with 1 and 4 children), utilizing only one genetic operation – mutation. Preliminary experiments indicate that our methodology yields promising results.
