2026· Proceedings of the 22nd International Conference on Web Information Systems and Technologies· 0 citations· 16 references
TL;DR
The proposed method exploits four Transformer architectures with the aim to distinguish between malicious and benign Android applications based on their opcode sequences, and reveals the opcode patterns that the models associate with malicious behavior, providing valuable insights into the malware detection model decision-making process.
Abstract
: Malware detection, particularly in mobile operating systems, remains a significant challenge due to the limited effectiveness of both free and commercial signature-based antimalware software in identifying zero-day threats. Signature-based approaches can only detect malware whose signatures have already been incorporated into their databases. Consequently, newly emerging malware must become sufficiently widespread before it can be reliably recognized by existing security solutions. In this paper, we propose a static malware detection method for mobile environments, with a particular focus on the Android platform (the most widespread one). The proposed method exploits four Transformer architectures with the aim to distinguish between malicious and benign Android applications based on their opcode sequences. To overcome the lack of explainability of deep learning models, we integrate two explainability techniques i.e., Integrated Gradi-ents and SHapley Additive exPlanations, to provide token-level explanations and identify the opcodes that contribute most significantly to the malware detection prediction i.e., the malicious payload from the model point of view. Experimental evaluations conducted on a real-world dataset composed by malicious and trusted Android applications demonstrate the effectiveness of the proposed approach. Furthermore, the explainability analysis reveals the opcode patterns that the models associate with malicious behavior, providing valuable insights into the malware detection model decision-making process. These findings suggest that the adoption of Transformer-based architectures with explainability techniques can offer an accurate and trustworthy solution that can support both end users and cybersecurity analysts in Android malware detection
Malware detection in mobile environment represents a crucial task, considering the inefficacy on signature-based antimalware to detect zero-day attacks. Researchers from academic and industrial community are proposing approaches based on machine learning, obtaining interesting performance in mobile malware detection bu...
F. Mercaldo, S. Schrittwieser, Patrick Kochberger et al.· 2026 International Conferenc...· 0 citations
The problem of Android malware is considered to be a big challenge for mobile cybersecurity because of its continuous evolution and evasion capabilities of the conventional signature-based approaches used in detecting malicious software. In this paper, we propose an effective Android Malware Detection System which comb...
Laith Sami· NTU Journal of Engineering a...· 0 citations
This work provides a robust and scalable semantic‐based detection framework for both host‐based and IoT security systems in an evolving malware landscape by exploiting persistent semantic characteristics that remain invariant across evolving variants within malware families.
Khizar Hayat, Sadaf Hina, Fabiha Hashmat et al.· Security and Privacy· 0 citations
Over the years, the number of attacks has increased drastically due to the rise of mobile devices. Due to this enormous number of attacks, protecting users' personal information has become essential. In this paper, we propose an explainable method for Android malware detection by exploiting Federated Machine Learning....
Giovanni Ciaramella, F. Martinelli, A. Santone et al.· 2026 International Conferenc...· 0 citations
Since Android is the mobile platform most targeted by malicious software, the accurate detection of new and evolving threats remains a critical challenge. Although deep learning-based malware detectors have improved detection performance, most existing methods rely on opaque models and provide limited interpretability,...
Narges Dehghan, Farnoush Manavi, A. Hamzeh· IEEE Access· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.