412 Hits in 7.2 sec

A Review on Malware Detection Methods

Jaishri M. Waghmare, Mayuri M. Chitmogrekar
2022 SAMRIDDHI A Journal of Physical Sciences Engineering and Technology  
This paper aims to conduct a brief and systematic survey on the malware detection methods based on the soft computing model.  ...  Recent methods for identifying malicious codes and threats have indicated less precision and deficient speeds.  ...  A hand in a picture, for example, remains a Figure 1 : Malware detection using data mining hand regardless of its location or alignment, but a hand in a text segment might be a noun or a verb based on  ... 
doi:10.18090/samriddhi.v14i01.6 fatcat:wnon2fdtmbcptmkiahelm7mlse

A Malicious Domain Detection Model Based on Improved Deep Learning

XiangDong Huang, Hao Li, Jiajia Liu, FengChun Liu, Jian Wang, BaoShan Xie, BaoPing Chen, Qi Zhang, Tao Xue, Shahid Mumtaz
2022 Computational Intelligence and Neuroscience  
on malicious domain detection.  ...  This article proposes a malicious domain name detection model based on improved deep learning, which can combine the advantages of three different network models, convolutional neural network (CNN), temporal  ...  To sum up, among the existing malicious domain name detection models, many improvement methods for CNN detection models mostly improve the detection effect by improving the model's character-level feature  ... 
doi:10.1155/2022/9241670 pmid:35795747 pmcid:PMC9252679 fatcat:o7ysa7ewvneyhkdroeqj363l34

Deep Learning for Vulnerability and Attack Detection on Web Applications: A Systematic Literature Review

Rokia Lamrani Alaoui, El Habib Nfaoui
2022 Future Internet  
(iv) It is important to create a corpus for web attacks detection in order to take full advantage of text mining in DL-based web attacks detection models construction.  ...  (v) It is essential to define a common framework for developing and comparing DL-based web attacks detection models.  ...  [51] proposed a CNN-based system for detecting web attacks.  ... 
doi:10.3390/fi14040118 fatcat:eskzafzzxjgqjeqj5etc63ecze

Semi-supervised based Unknown Attack Detection in EDR Environment

2020 KSII Transactions on Internet and Information Systems  
The proposed technology uses a combination of AutoEncoder and 1D CNN (1-Dimention Convolutional Neural Network) based on semi-supervised learning.  ...  As a result of the experiment, 37 unknown attacks were detected in the event log collected for one month in the actual commercial endpoint environment, and 26 of them were verified as malicious through  ...  Based on semi-supervised learning, data collected for one month from a commercial endpoint environment is assumed to be normal, and normal data and out-ofbounds data are detected.  ... 
doi:10.3837/tiis.2020.12.016 fatcat:no6o5drfejarng7d6slm4egixi

Character Level based Detection of DGA Domain Names

Bin Yu, Jie Pan, Jiaming Hu, Anderson Nascimento, Martine De Cock
2018 2018 International Joint Conference on Neural Networks (IJCNN)  
Recently several different deep learning architectures have been proposed that take a string of characters as the raw input signal and automatically derive features for text classification.  ...  Training and evaluating on a dataset with 2M domain names shows that there is surprisingly little difference between various convolutional neural network (CNN) and recurrent neural network (RNN) based  ...  Traditional machine learning methods for DGA detection based on the domain name string rely on extraction of predefined, human engineered lexical features, see e.g.  ... 
doi:10.1109/ijcnn.2018.8489147 dblp:conf/ijcnn/YuPHNC18 fatcat:hd3ztzvd75crtpaqzo2ij4hpla

DeepHTTP: Semantics-Structure Model with Attention for Anomalous HTTP Traffic Detection and Pattern Mining [article]

Yuqi Yu, Hanbing Yan, Hongchao Guan, Hao Zhou
2018 arXiv   pre-print
Traffic generated by access activities can record website status and user request information, which brings a great opportunity for network attack detection.  ...  Moreover, the application of attention mechanism can assist in discovering critical parts of anomalous traffic and further mining attack patterns.  ...  Since the model is trained based on normal samples, traffic not present in the training set is likely to be labeled as malicious.  ... 
arXiv:1810.12751v1 fatcat:ozbmmro355fmrhaxa2j7nrxubm

DeepHTTP: Anomalous HTTP Traffic Detection and Malicious Pattern Mining Based on Deep Learning [chapter]

Yuqi Yu, Hanbing Yan, Yuan Ma, Hao Zhou, Hongchao Guan
2020 Communications in Computer and Information Science  
In this work, we propose DeepHTTP, an HTTP traffic detection framework based on deep learning.  ...  The detection model is called AT-Bi-LSTM, which is based on Bidirectional Long Short-Term Memory (Bi-LSTM) with attention mechanism.  ...  Specifically, we cluster malicious traffic entries and perform pattern mining for each cluster. Then we can generate new rules based on the mined malicious patterns.  ... 
doi:10.1007/978-981-33-4922-3_11 fatcat:jffot3q6bncatetvnna6on24xy

A Deep Learning-based Fine-grained Hierarchical Learning Approach for Robust Malware Classification [article]

Ahmed Abusnaina, Mohammed Abuhamad, Hisham Alasmary, Afsah Anwar, Rhongho Jang, Saeed Salem, DaeHun Nyang, David Mohaisen
2020 arXiv   pre-print
to detect 88.52% of the malicious AEs.  ...  However, recent studies have shown that machine learning-based approaches are susceptible to adversarial attacks by adding junk codes to the binaries, for example, with an intention to fool those machine  ...  of the CNN-and DNN-based IoT malware detection systems on normal samples (i.e., non-adversarial).  ... 
arXiv:2005.07145v2 fatcat:vsiin3udfjfd7acelbdh5vkhiu

A Low Computational Cost Method for Mobile Malware Detection Using Transfer Learning and Familial Classification Using Topic Modelling

Saket Acharya, Umashankar Rawat, Roheet Bhatnagar, Shyi-Ming Chen
2022 Applied Computational Intelligence and Soft Computing  
Hence, there is a need for an approach that can efficiently detect novel malware variants with a minimum computational cost.  ...  This paper proposes a novel framework for detecting and clustering Android malware using the transfer learning and the topic modelling approach.  ...  is one of the most famous approaches for analyzing static source code features to detect Android malware. [4, 5] are some of the proposed detection methods based on the static analysis approach.  ... 
doi:10.1155/2022/4119500 fatcat:a3ybaf7rgrbgvmj22uflgutie4

Comparison of Malware Classification Methods using Convolutional Neural Network based on API Call Stream

Matthew Schofield, Gulsum Alicioglu, Bo Sun, Russell Binaco, Paul Turner, Cameron Thatcher, Alex Lam, Anthony Breitzman
2021 International journal of network security and its applications  
We present a Convolutional Neural Network (CNN) for malware type classification based on the API (Application Program Interface) calls.  ...  Malicious software is constantly being developed and improved, so detection and classification of malwareis an ever-evolving problem.  ...  Two different analytic features based on categorical vector and TF-IDF vector were used for the API call dataset, and then fed to the proposed CNN to classify the malware.  ... 
doi:10.5121/ijnsa.2021.13201 fatcat:vzrer3dmufeupih7akzcyksgwe

Using Static and Dynamic Malware features to perform Malware Ascription [article]

Jashanpreet Singh Sraw, Keshav Kumar
2021 arXiv   pre-print
In this paper, we employ various Static and Dynamic features of malicious executables to classify malware based on their family.  ...  the base estimator.  ...  Chen, “Detection of malicious code variants based on deep learning,” IEEE Trans. Industrial Informatics, vol. 14, no. 7, pp. 3187–3196, 2018.  ... 
arXiv:2112.02639v1 fatcat:63y3buhsbbh65mlvdzwmpmgqqu

Detecting Malware with an Ensemble Method Based on Deep Neural Network

Jinpei Yan, Yong Qi, Qifan Rao
2018 Security and Communication Networks  
Recent researches mainly use machine learning based methods heavily relying on domain knowledge for manually extracting malicious features.  ...  Then MalNet uses CNN and LSTM networks to learn from grayscale image and opcode sequence, respectively, and takes a stacking ensemble for malware classification.  ...  [13] first proposed to apply the data mining method to detect malware and used three different types of static features, respectively, PE head, string sequence, and byte sequence.  ... 
doi:10.1155/2018/7247095 fatcat:tmyysltalvhu7olp3ajynd2aqe

Malicious URL Detection Algorithm Based on Multi Neural Network Series

Weirong Xiu
2021 Converter  
The experimental results shows that the CATIR algorithm has significantly improved the accuracy of malicious URL detection based on traditional algorithms to 96.9%.  ...  In natural language processing related technologies, word vector features are extracted based on URLs, and the extracted URL information features and host information features are merged.  ...  Rong Wei et al [10] designed and implemented a malicious Web request detection system based on the CNN model for the URL structure of Web requests, drawing on the feature extraction principle of CNN  ... 
doi:10.17762/converter.209 fatcat:keq4zjmxrvgspce47bgimavmi4

A Survey of Android Malware Static Detection Technology Based on Machine Learning

Qing Wu, Xueling Zhu, Bo Liu
2021 Mobile Information Systems  
In this paper, we investigated Android applications' structure, analysed various sources of static features, reviewed the machine learning methods for detecting Android malware, studied the advantages  ...  To detect Android malware, researchers have proposed various techniques, among which the machine learning-based methods with static features of apps as input vectors have apparent advantages in code coverage  ...  Static detection based on machine learning has excellent classification ability for known malicious applications.  ... 
doi:10.1155/2021/8896013 doaj:9dc548d197fd404fbcd4ee962f374bde fatcat:mbuavifbmzfmjm3shzm4wcbm4a

Malware classification based on double byte feature encoding

Lin Li, Ying Ding, Bo Li, Mengqing Qiao, Biao Ye
2021 Alexandria Engineering Journal  
Li et al., Malware classification based on double byte feature encoding, Alexandria Eng. J. (2021), https://doi.  ...  Bytes file represented by hexadecimal for feature extraction.  ...  The static analysis methods of malicious code mainly include disassembly, decompiling, string extraction analysis, binary structure analysis and so on.  ... 
doi:10.1016/j.aej.2021.04.076 fatcat:ocrqbt4gpngj7cwg22exyq2x2i
« Previous Showing results 1 — 15 out of 412 results