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.
Abstract
The rapid evolution of malware variants has increasingly undermined traditional signature‐based detection techniques, which are easily evaded through obfuscation and polymorphism that preserve malicious functionality. This challenge is particularly acute in Internet of Things (IoT) environments, where device heterogeneity, resource constraints, and large‐scale deployment limit the adoption of heavyweight security mechanisms. As a result, IoT systems have become prime targets for sophisticated malware campaigns, including botnets, ransomware, and spyware, highlighting the need for adaptive, lightweight, and behaviourally robust detection approaches. This paper addresses a fundamental limitation of existing malware detection systems by exploiting persistent semantic characteristics that remain invariant across evolving variants within malware families. A comprehensive methodology combining static, dynamic, and memory analysis is employed to extract core semantic features that capture essential malicious behaviors. These features are used to construct compact semantic signatures capable of detecting previously unseen and zero‐day variants within the same family. Extensive experimental evaluation demonstrates that the proposed approach significantly improves detection accuracy while reducing the size of the signature database. Comparative analysis against three state‐of‐the‐art anti‐malware tools shows superior accuracy, lower memory overhead, and faster scanning performance. Overall, this work provides a robust and scalable semantic‐based detection framework for both host‐based and IoT security systems in an evolving malware landscape.
The rapid advancement of technology has significantly enhanced innovation, productivity, and connectivity across industries but has also empowered cybercriminals to develop increasingly sophisticated malware. This advanced malware poses serious challenges to cybersecurity, as traditional detection methods often fail to...
Hasan A. Anabousi, M. Abualhaj, A. Abu-Shareha et al.· Discover Artificial Intellig...· 3 citations
– Polymorphic malware changes the appearance of its code to evade detection while wisely preserving its nefarious intent. Changing encryption keys and decryption routines can make familiar threats appear different to scanners that rely on fixed byte patterns. Security monitoring on Internet of Things (IoT) devices must...
Simanta Saikia, F. A.· International Journal of Com...· 0 citations
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 decis...
F. Mercaldo, S. Schrittwieser, Patrick Kochberger et al.· Proceedings of the 22nd Inte...· 0 citations
This study proposes an advanced, integrated behavior-based malware classification and automated mitigation framework specifically engineered for Windows operating environments, and introduces a multi-class risk-scoring mechanism to streamline Security Operations Center (SOC) incident triage.
Sivaharish R., S. K., Lediyal S. et al.· Research & Review: Machi...· 0 citations
Malware continues to evolve through obfuscation, packing, polymorphism, and other evasion techniques, challenging traditional detection approaches. Data mining (DM) and machine learning (ML) is become important by the day for identifying malicious software through static characteristics, runtime behaviour, and combinat...
Saud Adam Abdulkadir, Nor Fazlida Mohd Sani, Aziah Asmawi et al.· Pertanika Journal of Artific...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.