Few-Shot Learning With Prototypical Networks for Improved Memory Forensics

Securing computer systems requires effective methods for malware detection. Memory forensics analyzes memory dumps to identify malicious activity, but faces challenges including large and complex datasets, constantly evolving malware threats, and limited labeled data for training algorithms among ot...

Full description

Saved in:
Bibliographic Details
Main Authors: Muhammad Fahad Malik, Ammara Gul, Ayesha Saadia, Faeiz M. Alserhani
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10980249/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850144669279715328
author Muhammad Fahad Malik
Ammara Gul
Ayesha Saadia
Faeiz M. Alserhani
author_facet Muhammad Fahad Malik
Ammara Gul
Ayesha Saadia
Faeiz M. Alserhani
author_sort Muhammad Fahad Malik
collection DOAJ
description Securing computer systems requires effective methods for malware detection. Memory forensics analyzes memory dumps to identify malicious activity, but faces challenges including large and complex datasets, constantly evolving malware threats, and limited labeled data for training algorithms among others. This research introduces a novel approach for malware detection using memory forensics and prototypical networks. As the first application of prototypical networks to the Dumpware10 dataset (to the best of authors knowledge), our findings highlight the potential of few-shot learning for memory forensics-based malware detection, opening new avenues for research in this domain. Prototypical networks are a type of few-shot learning algorithm that excels at classifying new categories with minimal examples. Utilizing the publicly available Dumpware10 dataset, which includes 10 malware classes and one benign class, we preprocess memory dumps using denoising and A-Hash functions to reduce noise and redundancy. The prototypical network is trained on the first four malware classes and the benign class. It’s then tested on a dataset with one additional class (first five malware classes and the benign class). We progressively increase the number of test classes to eleven. Within each training episode, five training images are used as support samples, with all remaining images designated as query samples. Our goal isn’t to predict exact class labels, but to assess the similarity between query images and prototypes using a distance metric. If the label of a prototype matches the query image and the distance falls below a threshold, it’s considered a true positive. This approach achieves an average accuracy of 92% with eleven classes, the highest across all scenarios and comparable to previous work using machine and deep learning algorithms on this dataset.
format Article
id doaj-art-e323ba3ab3604ae7a340b6809238e9a1
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-e323ba3ab3604ae7a340b6809238e9a12025-08-20T02:28:18ZengIEEEIEEE Access2169-35362025-01-0113793977940910.1109/ACCESS.2025.356580210980249Few-Shot Learning With Prototypical Networks for Improved Memory ForensicsMuhammad Fahad Malik0https://orcid.org/0009-0009-9720-1784Ammara Gul1https://orcid.org/0000-0002-5854-1075Ayesha Saadia2Faeiz M. Alserhani3https://orcid.org/0000-0002-0161-7147Department of Cyber Security, Air University, Islamabad, PakistanFaculty of Computing, Engineering, and Built Environment (CEBE), Birmingham City University, Birmingham, U.K.Department of Computer Science, Air University, Islamabad, PakistanDepartment of Computer Engineering and Networks, College of Computer and Information Sciences, Jouf University, Sakaka, Al Jowf, Saudi ArabiaSecuring computer systems requires effective methods for malware detection. Memory forensics analyzes memory dumps to identify malicious activity, but faces challenges including large and complex datasets, constantly evolving malware threats, and limited labeled data for training algorithms among others. This research introduces a novel approach for malware detection using memory forensics and prototypical networks. As the first application of prototypical networks to the Dumpware10 dataset (to the best of authors knowledge), our findings highlight the potential of few-shot learning for memory forensics-based malware detection, opening new avenues for research in this domain. Prototypical networks are a type of few-shot learning algorithm that excels at classifying new categories with minimal examples. Utilizing the publicly available Dumpware10 dataset, which includes 10 malware classes and one benign class, we preprocess memory dumps using denoising and A-Hash functions to reduce noise and redundancy. The prototypical network is trained on the first four malware classes and the benign class. It’s then tested on a dataset with one additional class (first five malware classes and the benign class). We progressively increase the number of test classes to eleven. Within each training episode, five training images are used as support samples, with all remaining images designated as query samples. Our goal isn’t to predict exact class labels, but to assess the similarity between query images and prototypes using a distance metric. If the label of a prototype matches the query image and the distance falls below a threshold, it’s considered a true positive. This approach achieves an average accuracy of 92% with eleven classes, the highest across all scenarios and comparable to previous work using machine and deep learning algorithms on this dataset.https://ieeexplore.ieee.org/document/10980249/Malware detectionmemory forensicsfew-shot learningprototypical networks
spellingShingle Muhammad Fahad Malik
Ammara Gul
Ayesha Saadia
Faeiz M. Alserhani
Few-Shot Learning With Prototypical Networks for Improved Memory Forensics
IEEE Access
Malware detection
memory forensics
few-shot learning
prototypical networks
title Few-Shot Learning With Prototypical Networks for Improved Memory Forensics
title_full Few-Shot Learning With Prototypical Networks for Improved Memory Forensics
title_fullStr Few-Shot Learning With Prototypical Networks for Improved Memory Forensics
title_full_unstemmed Few-Shot Learning With Prototypical Networks for Improved Memory Forensics
title_short Few-Shot Learning With Prototypical Networks for Improved Memory Forensics
title_sort few shot learning with prototypical networks for improved memory forensics
topic Malware detection
memory forensics
few-shot learning
prototypical networks
url https://ieeexplore.ieee.org/document/10980249/
work_keys_str_mv AT muhammadfahadmalik fewshotlearningwithprototypicalnetworksforimprovedmemoryforensics
AT ammaragul fewshotlearningwithprototypicalnetworksforimprovedmemoryforensics
AT ayeshasaadia fewshotlearningwithprototypicalnetworksforimprovedmemoryforensics
AT faeizmalserhani fewshotlearningwithprototypicalnetworksforimprovedmemoryforensics