240 Hits in 8.4 sec

Deep learning at the shallow end: Malware classification for non-domain experts

Quan Le, Oisín Boydell, Brian Mac Namee, Mark Scanlon
2018 Digital Investigation. The International Journal of Digital Forensics and Incident Response  
We present a Deep Learning based malware classification approach that requires no expert domain knowledge and is based on a purely data driven approach for complex pattern and feature identification.  ...  Moreover, these signatures are often limited to local, contiguous sequences within the data whilst ignoring their context in relation to each other and throughout the malware file as a whole.  ...  The appeal of the outlined deep learning approach for malware classification is two fold.  ... 
doi:10.1016/j.diin.2018.04.024 fatcat:aulmxt3mcvgddcxjqfycdzvanm

DeepMAL – Deep Learning Models for Malware Traffic Detection and Classification [article]

Gonzalo Marín, Pedro Casas, Germán Capdehourat
2020 arXiv   pre-print
In recent years, machine learning-based systems have gain popularity for network security applications, usually considering the application of shallow models, which rely on the careful engineering of expert  ...  Deep Learning (DL) models can solve this limitation using their ability to learn feature representations from raw, non-processed data.  ...  shallow-like based models, using domain expert knowledge to craft the input features; in Section V we introduce a variation of the detection problem using a multi-class, malware classification approach  ... 
arXiv:2003.04079v2 fatcat:z7fwmizkf5hz5aoqmdouhoceje

An investigation of a deep learning based malware detection system

Mohit Sewak, Sanjay K. Sahay, Hemant Rathore
2018 Proceedings of the 13th International Conference on Availability, Reliability and Security - ARES 2018  
We investigate a Deep Learning based system for malware detection.  ...  In the investigation, we experiment with different combination of Deep Learning architectures including Auto-Encoders, and Deep Neural Networks with varying layers over Malicia malware dataset on which  ...  Our work indicates that Deep Learning based architectures such as Auto-Encoders (for Feature Extraction) and Deep Neural Networks (for malware classification) may provide a very effective system for defense  ... 
doi:10.1145/3230833.3230835 dblp:conf/IEEEares/SewakSR18 fatcat:wxqgsiiykraqroyvw75preff34

Fusing Feature Engineering and Deep Learning: A Case Study for Malware Classification [article]

Daniel Gibert, Carles Mateu, Jordi Planes, Quan Le
2022 arXiv   pre-print
In this paper we present an hybrid approach to address the task of malware classification by fusing multiple types of features defined by experts and features learned through deep learning from raw data  ...  While traditional feature-based approaches rely on the manual design of hand-crafted features based on experts knowledge of the domain, deep learning approaches replace the manual feature engineering process  ...  Dublin, and the University of Lleida.  ... 
arXiv:2206.05735v1 fatcat:6sq6t2c6rrcojdobwpdu6whjzm

Malware classification using XGboost-Gradient Boosted Decision Tree

Rajesh Kumar, Geetha S
2020 Advances in Science, Technology and Engineering Systems  
We propose in this work a malware classification scheme that constructs a model using low-end computing resources and a very large balanced dataset for malware.  ...  The model can be trained in low computation resources at less time in 1315 seconds with a reduction in feature set without affecting the performance for classification.  ...  It uses a wider breadth of input patterns with embedding and shallow CNN. Deep learning has dramatically improved the state of art in object classification.  ... 
doi:10.25046/aj050566 fatcat:7fko7vaksvdh3ky5a7a3cjtani

Deep Learning for Android Malware Defenses: a Systematic Literature Review [article]

Yue Liu, Chakkrit Tantithamthavorn, Li Li, Yepang Liu
2022 arXiv   pre-print
Yet, no systematic literature review focusing on deep learning approaches for Android Malware defenses exists.  ...  To this end, employing deep learning techniques to thwart Android malware attacks has recently garnered considerable research attention.  ...  To this end, employing deep learning techniques to thwart Android malware attacks has recently garnered considerable research attention.  ... 
arXiv:2103.05292v2 fatcat:qruddq4gknfq7jx5wyrk5qu2eu

Adversarial Machine Learning Attacks and Defense Methods in the Cyber Security Domain [article]

Ihai Rosenberg and Asaf Shabtai and Yuval Elovici and Lior Rokach
2021 arXiv   pre-print
domain, where actual adversaries (e.g., malware developers) exist.  ...  This paper is the first to discuss the unique challenges of implementing end-to-end adversarial attacks in the cyber security domain, map them in a unified taxonomy, and use the taxonomy to highlight future  ...  malware detection subdomain.5.1.1 Attacking Traditional (Shallow) Machine Learning Malware Classifiers.  ... 
arXiv:2007.02407v3 fatcat:rj3qomvg4bfb5p3atsct4winji

Malware Binary Image Classification Using Convolutional Neural Networks

John Kiger, Shen-Shyang Ho, Vahid Heydari
2022 International Conference on Cyber Warfare and Security (ICIW)  
One of these cybersecurity tasks where machine learning may prove advantageous is malware analysis and classification.  ...  of the most common and time-consuming security tasks using machine learning.  ...  Acknowledgement This material is based upon work supported by the National Science Foundation under Grant No. 1753900.  ... 
doi:10.34190/iccws.17.1.59 fatcat:3xgqmm3syfe3lninuqg5dxeumu

Survey on Applications of Deep Learning and Machine Learning Techniques for Cyber Security

Mohammed I. Alghamdi
2020 International Journal of Interactive Mobile Technologies  
The research aimed to conduct an extensive study of machine learning and deep learning methods in cybersecurity.  ...  The research has examined three machine learning methods and three deep learning methods to study the most popular techniques used in cybersecurity.  ...  The experts have moved towards more advanced methods of machine learning, i.e. deep learning, to overcome the limitations of shallow learning.  ... 
doi:10.3991/ijim.v14i16.16953 doaj:630bd6d43a51425ba094ccfe28068d4f fatcat:g2lbzcknzrf5lor7x2gvruo2jm

Malware Detection by Eating a Whole EXE [article]

Edward Raff, Jon Barker, Jared Sylvester, Robert Brandon, Bryan Catanzaro, Charles Nicholas
2017 arXiv   pre-print
In this work we introduce malware detection from raw byte sequences as a fruitful research area to the larger machine learning community.  ...  In doing so we will discuss the many challenges in building a neural network to process data at this scale, and the methods we used to work around them.  ...  Acknowledgments Special thanks to Mark McLean of the Laboratory for Physical Sciences for supporting this work.  ... 
arXiv:1710.09435v1 fatcat:scsvhk3rjvh7tlrhn754p634hi

Editorial Deep Learning for Anomaly Detection

Guansong Pang, Charu Aggarwal, Chunhua Shen, Nicu Sebe
2022 IEEE Transactions on Neural Networks and Learning Systems  
Editorial Deep Learning for Anomaly Detection A NOMALY detection aims at identifying data points which are rare or significantly different from the majority of data points.  ...  The work uses 11 deep methods from three general categories of approach, including generic normality feature learning, anomaly-measure dependent feature learning, and end-to-end anomaly scoring.  ...  Before joining SMU, he was a Research Fellow with the Australian Institute for Machine Learning (AIML), The University of Adelaide, Adelaide, SA, Australia.  ... 
doi:10.1109/tnnls.2022.3162123 fatcat:445bcedulbbppdmnzbgyvyuzd4

Malware Detection of Hangul Word Processor Files Using Spatial Pyramid Average Pooling

Young-Seob Jeong, Jiyoung Woo, SangMin Lee, Ah Reum Kang
2020 Sensors  
New malware for HWP files continues to appear because of the circumstances between South Korea and North Korea.  ...  Hangul Word Processor (HWP) is software for editing non-executable text files and is widely used in South Korea.  ...  when given carefully designed inputs based on domain knowledge, but these studies have a strong downside, as they require large amounts of effort from domain experts whenever new malware appears.  ... 
doi:10.3390/s20185265 pmid:32942607 fatcat:z3mlphgkzjbftpdykdkcbkio74

Robust Intelligent Malware Detection Using Deep Learning

Vinayakumar R, Mamoun Alazab, Soman KP, Prabaharan Poornachandran, Sitalakshmi Venkatraman
2019 IEEE Access  
To fill the gap in the literature, this paper, first, evaluates the classical MLAs and deep learning architectures for malware detection, classification, and categorization using different public and private  ...  Third, our major contribution is in proposing a novel image processing technique with optimal parameters for MLAs and deep learning architectures to arrive at an effective zero-day malware detection model  ...  ACKNOWLEDGEMENT The authors would like to thank NVIDIA India, for the GPU hardware support to research grant.  ... 
doi:10.1109/access.2019.2906934 fatcat:hr4vctlh55cbhamkvh5fq2hubu

Detecting Malicious PowerShell Commands using Deep Neural Networks [article]

Danny Hendler, Shay Kels, Amir Rubin
2018 arXiv   pre-print
This highlights the urgent need of developing effective methods for detecting malicious PowerShell commands.In this work, we address this challenge by implementing several novel detectors of malicious  ...  all these reasons, PowerShell is increasingly used by cybercriminals as part of their attacks' tool chain, mainly for downloading malicious contents and for lateral movement.  ...  Deep learning approaches are increasingly used in recent years for malware detection.  ... 
arXiv:1804.04177v2 fatcat:qausww3kp5fsdddkqqzkyyb6gi

The rise of machine learning for detection and classification of malware: Research developments, trends and challenges

Daniel Gibert, Carles Mateu, Jordi Planes
2020 Journal of Network and Computer Applications  
This survey aims at providing a systematic and detailed overview of machine learning techniques for malware detection and in particular, deep learning techniques.  ...  The main contributions of the paper are: (1) it provides a complete description of the methods and features in a traditional machine learning workflow for malware detection and classification, (2) it explores  ...  This research article has received a grant (2019 call) from the University of Lleida Language Institute to review the English.  ... 
doi:10.1016/j.jnca.2019.102526 fatcat:3bf6afjqpnb53eoeghfxjeaus4
« Previous Showing results 1 — 15 out of 240 results