ADVANCED IMAGE-BASED MALWARE DETECTION LEVERAGING SPARSE LSTM NETWORKS FOR INTELLIGENT FEATURE RECOGNITION AND CLASSIFICATION
Malware is a form of malicious software designed to cause harm to computer systems. In recent years, the proliferation of malware for illegal and malicious purposes has grown significantly. To counter these threats, several machine learning and deep learning techniques have been employed for the detection and classification of malware. One promising approach is image-based malware detection, which leverages machine learning and compuer vision models to analyse the visual representation of malware, such as binary images or screenshots, for detecting malicious behaviours. This method has the potential to identify hidden or polymorphic malware variants, providing an additional layer of defence against emerging cyber-attacks. In this study, a new approach is introduced that utilizes a Sparse Long Short-Term Memory (LSTM) network for image-based malware classification. The primary objective of this method is to employ an optimized deep learning model to efficiently identify and classify malware images. The Sparse LSTM network is used to extract crucial feature vectors from the malware images, enhancing the classification process. By integrating attention mechanisms, the model effectively captures significant patterns for malware recognition. The technique is evaluated using the Malimg malware data set, demonstrating promising results in comparison to existing methods.
"ADVANCED IMAGE-BASED MALWARE DETECTION LEVERAGING SPARSE LSTM NETWORKS FOR INTELLIGENT FEATURE RECOGNITION AND CLASSIFICATION", TIJER - TIJER - INTERNATIONAL RESEARCH JOURNAL (www.TIJER.org), ISSN:2349-9249, Vol.12, Issue 4, page no.a900-a928, April-2025, Available :https://tijer.org/TIJER/papers/TIJER2504129.pdf
Volume 12
Issue 4,
April-2025
Pages : a900-a928
Paper Reg. ID: TIJER_157572
Published Paper Id: TIJER2504129
Downloads: 000273
Research Area: Science and Technology
Country: Shirwal, Maharashtra, India
ISSN: 2349-9249 | IMPACT FACTOR: 8.57 Calculated By Google Scholar | ESTD YEAR: 2014
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.57 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Publisher: TIJER (IJ Publication) Janvi Wave
