Filters








2,140 Hits in 3.6 sec

Malware classification with LSTM and GRU language models and a character-level CNN

Ben Athiwaratkun, Jack W. Stokes
2017 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
We also propose using an attention mechanism similar to [12] from the machine translation literature, in addition to temporal max pooling used in [1], as an alternative way to construct the file representation  ...  Finally, we propose a new single-stage malware classifier based on a character-level convolutional neural network (CNN).  ...  Attention Mechanism: Bahdanau et al. [12] recently proposed a new attention mechanism to align the input and output sentences (i.e. sequences) in the context of neural machine translation.  ... 
doi:10.1109/icassp.2017.7952603 dblp:conf/icassp/AthiwaratkunS17 fatcat:wkb2o2w65zcopbx6n7jqdxchym

Image-Based Malware Classification Using VGG19 Network and Spatial Convolutional Attention

Mazhar Javed Awan, Osama Ahmed Masood, Mazin Abed Mohammed, Awais Yasin, Azlan Mohd Zain, Robertas Damaševičius, Karrar Hameed Abdulkareem
2021 Electronics  
In this paper, we propose a spatial attention and convolutional neural network (SACNN) based on deep learning framework for image-based classification of 25 well-known malware families with and without  ...  The results indicate that our proposed model can be used for image-based malware detection with high performance, despite being simpler as compared to other available solutions.  ...  Spatial Attention Mechanism The attention mechanism first became popular as an enhancement for encoder decoderbased neural machine translation systems.  ... 
doi:10.3390/electronics10192444 fatcat:ijnf3k3275gcdhae7sidiumw2i

Attention-Based Automated Feature Extraction for Malware Analysis

Sunoh Choi, Jangseong Bae, Changki Lee, Youngsoo Kim, Jonghyun Kim
2020 Sensors  
In this study, we propose a malicious file feature extraction method based on attention mechanism.  ...  First, by adapting the attention mechanism, we can identify application program interface (API) system calls that are more important than others for determining whether a file is malicious.  ...  Attention Mechanism Attention is a deep learning mechanism that looks for the parts of sequence data with greater impacts on the results.  ... 
doi:10.3390/s20102893 pmid:32443750 fatcat:ggdjewjdwff2jj4anh5db5pn4e

A Novel Malware Detection and Family Classification Scheme for IoT Based on DEAM and DenseNet

Changguang Wang, Ziqiu Zhao, Fangwei Wang, Qingru Li, Athanasios V. Vasilakos
2021 Security and Communication Networks  
In this paper, a new simple and effective attention module of Convolutional Neural Networks (CNNs), named as Depthwise Efficient Attention Module (DEAM), is proposed and combined with a DenseNet to propose  ...  With the rapid increase in the amount and type of malware, traditional methods of malware detection and family classification for IoT applications through static and dynamic analysis have been greatly  ...  With the development of neural networks in recent years, static analysis and dynamic analysis are often combined with neural networks for malware detection and family classification.  ... 
doi:10.1155/2021/6658842 fatcat:u2lplch3ardynn2tggpdxca7gy

Attention in Recurrent Neural Networks for Ransomware Detection

Rakshit Agrawal, Jack W. Stokes, Karthik Selvaraj, Mady Marinescu
2019 ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
We present specialized recurrent neural networks for capturing local event patterns in ransomware sequences using the concept of attention mechanisms.  ...  With an ability to lock out user access to their content, recent ransomware attacks have caused severe impact at an individual and organizational level.  ...  We performed an analysis of the execution behavior of ransomware Portable Executable files and compared them with regular malware, as well as with benign executable files.  ... 
doi:10.1109/icassp.2019.8682899 dblp:conf/icassp/AgrawalSSM19 fatcat:5kf5rgipl5arbnvfjziocxtyfe

TagSeq: Malicious behavior discovery using dynamic analysis

Yi-Ting Huang, Yeali S. Sun, Meng Chang Chen, Robertas Damaševičius
2022 PLoS ONE  
Moreover, we utilize an attention mechanism to capture the relations between generated tags and certain API invocation calls.  ...  In recent years, studies on malware analysis have noticeably increased in the cybersecurity community.  ...  This has been also applied to malware analysis [11] to visualize important region of byte sequences. Thus, we adopt attention mechanism to align a generated tag to each API call.  ... 
doi:10.1371/journal.pone.0263644 pmid:35576222 pmcid:PMC9109923 fatcat:hjzcuzu5hzgkhgjafu6yhmjxma

Ransomware Protection Tool based on Recurrent Neural Network (RNN)

Nandhini S
2020 International Journal for Research in Applied Science and Engineering Technology  
We extant specific recurrent neural networks for catching resident happening designs in ransomware orders using the idea of attention mechanisms.  ...  According to Bitdefender "Ransomware is a form of malicious software (or malware) that, once it's taken over your computer, threatens you with harm, usually by denying you access to your data.  ...  We extant a new recurrent neural network constituent for manipulating the reiterating patterns by including attention mechanisms on the ideas of a arrangement knowledge module.  ... 
doi:10.22214/ijraset.2020.5325 fatcat:qbesh23tqvhg7lz2ya3fjtxwm4

How to Make Attention Mechanisms More Practical in Malware Classification

Xin Ma, Shize Guo, Haiying Li, Zhisong Pan, Junyang Qiu, Yu Ding, Feiqiong Chen
2019 IEEE Access  
Also, we construct a new classification framework based on attention mechanism and Convolutional Neural Networks mechanism.  ...  Machine learning has been widely used in the field of malware classification, but some emerging studies, such as attention mechanisms, are rarely applied in this field.  ...  DATA AVAILABILITY Research Data Related to this Submission Title: Microsoft 2015 contest dataset Repository: malware classification dataset url: https://www.kaggle.com/c/malware-classification/  ... 
doi:10.1109/access.2019.2948358 fatcat:6f4it2hipnenlijgycu4eo32ze

Malware Detection Based on Graph Attention Networks for Intelligent Transportation Systems

Cagatay Catal, Hakan Gunduz, Alper Ozcan
2021 Electronics  
To detect malware attacks addressing ITS, a Graph Attention Network (GAN)-based framework is proposed in this study.  ...  The main objective of this study is to improve the performance of malware detection models using Graph Attention Networks.  ...  Malware detection approaches are generally divided into three main categories, namely static analysis, dynamic analysis, and hybrid analysis.  ... 
doi:10.3390/electronics10202534 fatcat:akgkn5cp6baodoqesyh4vlprlm

Why an Android App is Classified as Malware? Towards Malware Classification Interpretation [article]

Bozhi Wu, Sen Chen, Cuiyun Gao, Lingling Fan, Yang Liu, Weiping Wen, Michael R. Lyu
2020 arXiv   pre-print
Our study peeks into the interpretable ML through the research of Android malware detection and analysis.  ...  classification phase of XMal hinges multi-layer perceptron (MLP) and attention mechanism, and also pinpoints the key features most related to the classification result. (2) The second interpreting phase  ...  With the popularity of deep neural networks, people began to utilize the deep neural network models for malware detection [23, 32, 40, 57, 61] . Yu et al.  ... 
arXiv:2004.11516v2 fatcat:l6g6unutlrclbpjdoocgrvs6hu

Android Malware Analysis and Detection Based on Attention-CNN-LSTM

Luo shiqi
2019 Journal of Computers  
This paper proposes an Android malware analysis and detection technology based on Attention-CNN-LSTM, which is a types of Multimodel Deep Learning.  ...  Dynamic analysis methods: the dynamic analysis methods of malware (such as active defense technology and cloud killing technology) have been used by more security vendors with the development of anti-malware  ...  Attention mechanism. Fig. 7 .Fig. 8 . 78 Convolutional LSTM model.  ... 
doi:10.17706/jcp.14.1.31-43 fatcat:v3q3ukdjsjfe5mj2ee6p7ppk7q

Learning Malware Representation based on Execution Sequences [article]

Yi-Ting Huang, Ting-Yi Chen, Yeali S. Sun, Meng Chang Chen
2021 arXiv   pre-print
Malware analysis has been extensively investigated as the number and types of malware has increased dramatically.  ...  The encoder comprises gated recurrent units (GRU) to preserve the ordinal position of API calls and a self-attention mechanism for comparing intra-relations among different positions of API calls.  ...  The MLP is a traditional neural network in which we use two fully connected layers without any recurrent neural units or attention mechanism.  ... 
arXiv:1912.07250v2 fatcat:jtzmueddvfftxbllsiqe6yr5hq

Black-Box Attacks against RNN based Malware Detection Algorithms [article]

Weiwei Hu, Ying Tan
2017 arXiv   pre-print
These works mainly focused on the detection algorithms which use features with fixed dimension, while some researchers have begun to use recurrent neural networks (RNN) to detect malware based on sequential  ...  Then we propose a generative RNN to output sequential adversarial examples from the original sequential malware inputs.  ...  Dataset We crawled 180 programs with corresponding behavior reports from a website for malware analysis (https://malwr.com/).  ... 
arXiv:1705.08131v1 fatcat:k4geg2grdngy5meiycdrwhzp7q

Leveraging attention-based deep neural networks for security vetting of Android applications

Prabesh Pathak, Prabesh Poudel, Sankardas Roy, Doina Caragea
2021 EAI Endorsed Transactions on Security and Safety  
In our experiment, we work with two attention-based models: Bi-LSTM Attention and Self-Attention. Our classification models achieve high accuracy in malware detection.  ...  In this paper, using the attention mechanism, we aim to find the API-calls that are predictive with respect to the maliciousness of Android apps.  ...  Prior research [6, 7] in the domain of Neural Machine Translation (NMT) showed that a Bi-LSTM combined with the attention mechanism holds even better promise, as the use of attention mechanism allows  ... 
doi:10.4108/eai.27-9-2021.171168 fatcat:is7xf2c2anbmzlj5pv43jzikii

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

Yue Liu, Chakkrit Tantithamthavorn, Li Li, Yepang Liu
2022 arXiv   pre-print
To this end, employing deep learning techniques to thwart Android malware attacks has recently garnered considerable research attention.  ...  However, given the explosive growth of Android malware and the continuous advancement of malicious evasion technologies like obfuscation and reflection, Android malware defense approaches based on manual  ...  Although there is currently only one primary study employing attention mechanisms, a variety of popular attention mechanisms have been proposed and demonstrated to perform well in NLP or CV, such as self-attention  ... 
arXiv:2103.05292v2 fatcat:qruddq4gknfq7jx5wyrk5qu2eu
« Previous Showing results 1 — 15 out of 2,140 results