Filters








34,312 Hits in 4.2 sec

Malicious Code Detection and Acquisition Using Active Learning

Robert Moskovitch, Nir Nissim, Yuval Elovici
2007 2007 IEEE Intelligence and Security Informatics  
Detection of known malicious code is commonly performed by anti-virus tools. These tools detect the known malicious code using signature detection methods.  ...  Recent studies have shown that machine learning methods can be used for detecting unknown malicious executables based on their binary code.  ... 
doi:10.1109/isi.2007.379505 dblp:conf/isi/MoskovitchNE07 fatcat:az2xqn4lzrdizadtqed5lwhvvm

Polymorphic Malicious JavaScript Code Detection for APT Attack Defence

Choi, You, Choi, Kim
2015 Journal of universal computer science (Online)  
The majority of existing malware detection techniques detects malicious codes by identifying malicious behavior patterns.  ...  code detection methods.  ...  Learning script code pattern using SVM The codes related on malicious activity are extracted to use the converted CGIF codes through malicious script analysis.  ... 
doi:10.3217/jucs-021-03-0369 fatcat:nux7m65l4bfudj3gew3f4idida

Deep Packet Filtering Mechanism for Secure Internetworks

Hyun Woo Kim and Eun Et.al
2021 Turkish Journal of Computer and Mathematics Education  
After performing the word embedding process on the extracted sequence data using the word2vec technique, it detects malicious packets on the network by learning the LSTM model.  ...  Since DPFM proceeds at the network boundary to analyze and extract malicious packets, primary detection is possible.  ...  To build a malicious code detection model, 281 malicious codes and 270 non-malicious files were used as data sets.  ... 
doi:10.17762/turcomat.v12i6.1956 fatcat:cpvos7ec55ghvba5yf6fz2p47u

Autonomous learning for detection of JavaScript attacks

Guido Schwenk, Alexander Bikadorov, Tammo Krueger, Konrad Rieck
2012 Proceedings of the 5th ACM workshop on Security and artificial intelligence - AISec '12  
The results of our study are mixed: For manually verified data excellent detection rates up to 93% are achievable, yet for fully automated learning only 67% of the malicious code is identified.  ...  In this paper, we present an empirical study of a fully automated system for collecting, analyzing and detecting malicious JavaScript code.  ...  The system (a) retrieves benign and malicious JavaScript code from the Internet, (b) identifies malicious functionality using client-based honeypots and (c) learns a detection model from features of static  ... 
doi:10.1145/2381896.2381911 dblp:conf/ccs/SchwenkBKR12 fatcat:vvqfprpyz5dr7hb44wkoweqyb4

Intelligent Defense against Malicious JavaScript Code

Tammo Krueger, Konrad Rieck
2012 PIK - Praxis der Informationsverarbeitung und Kommunikation  
A lightweight static and dynamic analysis is performed, which enables learning and detecting malicious patterns in the structure and behavior of JavaScript code.  ...  In this article, we present Cujo, a learning-based system for detection and prevention of JavaScript attacks.  ...  To this end, sensors either actively seek for malicious activity using low-interaction honeyclients [ , , ] or passively acquire attacks using monitoring techniques, such as spamtraps.  ... 
doi:10.1515/pik-2012-0009 fatcat:34pjgv35jjbfdil3uwbr6z4rwm

Intelligent Defense against Malicious JavaScript Code

Tammo Krueger, Konrad Rieck
2012 PIK - Praxis der Informationsverarbeitung und Kommunikation  
A lightweight static and dynamic analysis is performed, which enables learning and detecting malicious patterns in the structure and behavior of JavaScript code.  ...  In this article, we present Cujo, a learning-based system for detection and prevention of JavaScript attacks.  ...  To this end, sensors either actively seek for malicious activity using low-interaction honeyclients [ , , ] or passively acquire attacks using monitoring techniques, such as spamtraps.  ... 
doi:10.1515/pik-2012-0009piko.2012.35.1.54 fatcat:jrfvhtbi7reeva5a3y2jc7h4qa

A Survey on Techniques to Detect Malicious Activites on Web

Abdul Rahaman Wahab Sait, Dr.M.Arunadevi, Dr.T.Meyyappan
2019 International Journal of Advanced Computer Science and Applications  
Terrorist are using web as a weapon to propaganda false information. Many innocent youths were trapped by web terrorist. It is very difficult to trace the impression of malicious activities on web.  ...  The world wide web is more vulnerable for malicious activities.  ...  Machine learning methods are the solution for the detection of malicious activities. The future work will be a development of detection technique to detect malicious activities on web.  ... 
doi:10.14569/ijacsa.2019.0100226 fatcat:yongiihdhjf7zflimnlrds7vd4

A Neural Network Based Hybrid Approach for Analysing and Detecting Malware Threat in Android Applications

Hetal Suresh, Joseph Raymond V
2018 International Journal of Engineering & Technology  
In this project, our purpose is to identify the malicious applications using Machine learning.  ...  By combining both static analysis and dynamic analysis we can use a Hybrid approach for analysing and detecting malware threats in android applications using Recurrent Neural Network (RNN).  ...  To predict the malicious code or activity of an application we analyse a code with the set of various malicious code and train our machine.  ... 
doi:10.14419/ijet.v7i4.6.28452 fatcat:av4p3etwdjcdjc4m5kd3zwm5oi

Stimulation and Detection of Android Repackaged Malware with Active Learning [article]

Aleieldin Salem
2018 arXiv   pre-print
We implemented an architecture, Aion, that connects the processes of stimulating and detecting repackaged malware using a feedback loop depicting active learning.  ...  Our evaluation of a sample implementation of Aion using two malware datasets (Malgenome and Piggybacking) shows that active learning can outperform conventional detection techniques and, hence, has great  ...  Using a sample implementation of our proposed active learning architecture Aion, we used active learning to stimulate, analyze, and detect Android repackaged malware.  ... 
arXiv:1808.01186v1 fatcat:afz7t3y62zf7pihyo3ytwvsvhq

Research on Intrusion Detection Systems and Unknown Malcode Detection based on Network Behavior

Xiaoyong YU
2016 International Journal of Security and Its Applications  
In this paper, based on the analysis of malicious code detection technology and detection system, the author designs and implements an unknown malicious code detection system based on network behavior  ...  In all kinds of Internet security incidents, the most serious is malicious code.  ...  malicious code, network maintenance of normal use.  ... 
doi:10.14257/ijsia.2016.10.5.30 fatcat:vwxq5fu4kbh7zhrza6xwghsswa

Detecting malicious applications on Android is based on static analysis using Deep Learning algorithm

Lai Van Duong
2020 International Journal of Advanced Trends in Computer Science and Engineering  
In this paper, we will propose the use of static analysis techniques to build a behavior of malicious code in the application and machine learning algorithms to detect malicious behavior.  ...  Therefore, to prevent the attack and distribution of malware through Android apps, it is necessary to research the method of detecting malicious code from the time users download applications to their  ...  MODEL OF DETECTING MALICIOUS ON ANDROID USING MACHINE LEARNING Detection model Figure 3 depicts a model of the malware detection method on the android application using the machine learning algorithm  ... 
doi:10.30534/ijatcse/2020/154932020 fatcat:e534sbcs45eqlkuy7s4ed5howi

A machine learning approach to detection of JavaScript-based attacks using AST features and paragraph vectors

Samuel Ndichu, Sangwook Kim, Seiichi Ozawa, Takeshi Misu, Kazuo Makishima
2019 Applied Soft Computing  
[23] infer behavior model or typical behavior of malicious JS by active automata learning using Deterministic Finite Automaton (DFA).  ...  The retraining would achieve even higher accuracy for the task of detection of malicious JS code content using Doc2Vec for a JS code content feature learning.  ... 
doi:10.1016/j.asoc.2019.105721 fatcat:5womgprqu5gmlpxwt2tq2cbefi

MALICIOUS JAVASCRIPT DETECTION BASED ON CLUSTERING TECHNIQUES

Nguyen Hong Son, Ha Thanh Dung
2021 Zenodo  
So far, the alternative methods using machine learning have achieved encouraging results, and have detected malicious JavaScript code with high accuracy.  ...  The rapid growth of malicious JavaScript is a real challenge to the solutions based on supervised learning due to the lacking of experience in detecting new forms of malicious JavaScript code.  ...  So far, the alternative methods using machine learning have achieved encouraging results, and have detected malicious JavaScript code with high accuracy.  ... 
doi:10.5281/zenodo.5763066 fatcat:k4iexynvjvgf3dylblbyndpwmq

Early detection of malicious behavior in JavaScript code

Kristof Schütt, Marius Kloft, Alexander Bikadorov, Konrad Rieck
2012 Proceedings of the 5th ACM workshop on Security and artificial intelligence - AISec '12  
The method uses machine learning techniques for jointly optimizing the accuracy and the time of detection.  ...  Malicious JavaScript code is widely used for exploiting vulnerabilities in web browsers and infecting users with malicious software.  ...  Similar learning methods are also applied in other detectors for malicious JavaScript code. For example, IceShield uses linear discriminant analysis for detection of malicious code.  ... 
doi:10.1145/2381896.2381901 dblp:conf/ccs/SchuttKBR12 fatcat:f57fi52xjbdq3etywpv3gap7iq

Deep Learning and Regularization Algorithms for Malicious Code Classification

Haojun Wang, Haixia Long, Ailan Wang, Tianyue Liu, Haiyan Fu
2021 IEEE Access  
ACKNOWLEDGMENT The authors appreciate Jialiang Yang and others for useful discussions.  ...  The method used in this paper is effective in malicious code detection.  ...  EVALUATION METRICS The deep learning used in this article belongs to the field of machine learning, and malicious code detection belongs to the multi-classification problem in machine learning problems  ... 
doi:10.1109/access.2021.3090464 fatcat:x6mlqkhzlzggdo2gioq2tqb2ai
« Previous Showing results 1 — 15 out of 34,312 results