Please use this identifier to cite or link to this item:
http://hdl.handle.net/2080/4579
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Rajneekant, . | - |
dc.contributor.author | Kishore, Pushkar | - |
dc.contributor.author | Gond, Bishwajit Prasad | - |
dc.contributor.author | Mohapatra, Durga Prasad | - |
dc.date.accessioned | 2024-05-28T13:26:35Z | - |
dc.date.available | 2024-05-28T13:26:35Z | - |
dc.date.issued | 2024-05 | - |
dc.identifier.citation | International Conference on Innovations and Advances in Cognitive Systems(ICIACS), Builders Engineering College, Kangayam, Tamil Nadu, India, 27-28 May 2024 | en_US |
dc.identifier.uri | http://hdl.handle.net/2080/4579 | - |
dc.description | Copyright belongs to proceeding publisher | en_US |
dc.description.abstract | The exponential rise in malware is a significant threat to the current hosts and it necessitates robust detection and classification mechanisms. Traditional analysis methods like static and dynamic analysis do not successfully identify malware due to evasion techniques. Dynamic techniques can uncover behavior-hiding malware but require a sophisticated malware detector. Current malware detectors use API sequences for detection but overlook the significance of API arguments. To address the limitations, we propose using Levenshtein distance for evaluating the embedding of API calls and thereby enhancing the feature representation. Later, we construct a graphical network from API embeddings and an appropriate graph neural network model is proposed to derive patterns from the provided graphical structures. The proposed malware detector/classifier achieves 99.59% malware detection Matthews Correlation Coefficient score and 74.39% malware classification Matthews Correlation Coefficient score. Overall, the proposed model aims to help understand malware behaviors, improve API call embedding, and detectstealthy malicious samples. | en_US |
dc.subject | Malicious samples | en_US |
dc.subject | API call arguments | en_US |
dc.subject | API call embedding | en_US |
dc.subject | Graph neural network | en_US |
dc.title | Malware Detector and Classifier using API Call Embedding and Graph Neural Networks | en_US |
dc.type | Article | en_US |
Appears in Collections: | Conference Papers |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
2024_ICIACS_Rajnikant_Malware.pdf | 332.01 kB | Adobe PDF | View/Open Request a copy |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.