Building a practical and reliable classifier for malware detection

Vatamanu, Cristina; Gavriluţ, Dragoş Teodor; Benchea, Răzvan-Mihai

doi:10.1007/s11416-013-0188-1

Cited by 11 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neural networks are algorithms used primarily to solve classification problems [18], [19]. Self Organizing Maps (SOM), also called Kohonen maps, are a special type of neural networks used in the field of Unsupervised Machine Learning.…”

Section: A Som For Minmax Multiple-tspmentioning

confidence: 99%

SOM-Guided Evolutionary Search for Solving MinMax Multiple-TSP

Lupoaie¹,

Chili²,

Breaban

et al. 2019

2019 IEEE Congress on Evolutionary Computation (CEC)

View full text Add to dashboard Cite

Multiple-TSP, also abbreviated in the literature as mTSP, is an extension of the Traveling Salesman Problem that lies at the core of many variants of the Vehicle Routing problem of great practical importance. The current paper develops and experiments with Self Organizing Maps, Evolutionary Algorithms and Ant Colony Systems to tackle the MinMax formulation of the Single-Depot Multiple-TSP. Hybridization between the neural network approach and the two meta-heuristics shows to bring significant improvements, outperforming results reported in the literature on a set of problem instances taken from TSPLIB.

show abstract

Section: A Som For Minmax Multiple-tspmentioning

confidence: 99%

SOM-Guided Evolutionary Search for Solving MinMax Multiple-TSP

Lupoaie¹,

Chili²,

Breaban

et al. 2019

2019 IEEE Congress on Evolutionary Computation (CEC)

View full text Add to dashboard Cite

show abstract

“…Nissim et al 13 applied SVM on a carefully selected feature set and get the state-of-art detection performances. Another malware detection algorithm proposed by Vatamanu et al 22 makes use of simple perceptron learning algorithms and aggregate perceptrons to solve large scale malware detection problem. Accordingly, the most popular machine learning algorithms for malware detection include kernel methods like SVM and ensemble learning methods like boosting and voted perceptrons.…”

Section: Machine Learning Algorithmsmentioning

confidence: 99%

An Ensemble Cost-Sensitive One-Class Learning Framework for Malware Detection

Liu

Song

Miao

et al. 2015

Int. J. Patt. Recogn. Artif. Intell.

View full text Add to dashboard Cite

Machine learning is among the most popular methods in designing unknown and variant malware detection algorithms. However, most of the existing methods take a single type of features to build binary classi¯ers. In practice, these methods have limited ability in depicting malware characteristics and the binary classi¯cation su®ers from inadequate sampling of benign samples and extremely imbalanced training samples when detecting malware. In this paper, we present a malware detection Framework based on ENsemble One-Class Learning, namely FENOC. It uses hybrid features at di®erent semantic layers to ensure a comprehensive insight of the program to be analyzed. We construct the malware detector by a novel learning algorithm called Cost-sensitive Twin One-class Classi¯er (CosTOC), which uses a pair of one-class clas-si¯ers to describe malware and benign programs respectively. CosTOC is more°exible and robust in comparison to conventional binary classi¯ers when training samples are extremely imbalanced or the benign programs are inadequately sampled. Finally, random subspace method and clustering-based ensemble method are developed to enhance the generalization ability of CosTOC. Experimental results show that FENOC gives a comparative detection rate and a lower false positive rate than many other binary classi¯cation algorithms, especially when the detector are trained with imbalanced data, or evaluated in terms of false positive rate.

show abstract

“…Because of the insensitive data used previously, Hadoop was not had that much of importance [4]- [6]. What makes it imperfect, limited access solution to the cluster cloud and other systems with traditional methods, which designed to process structured data such as data warehouse and management systems of a relational database are unable to handle large-scale data of unstructured type using an effective way [7]. Thus, HDFS is used to deal with such data type of sensitive and personal information, but its problems still existed until that time, especially in its authentication where it is possible for any user to penetrate and spy another user or cluster services [8].…”

Section: Introductionmentioning

confidence: 99%

Static Knowledge-Based Authentication Mechanism for Hadoop Distributed Platform using Kerberos

Algaradi¹,

Rama²

2019

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

With the quickened phenomenal expansion of data, storing massive data has become important and increasingly growing day by day. Thus, big data came to express this large data and handling it properly under three important characteristics such as volume, veracity, and Variety. One practical of big data problems is user and services authentication. Kerberos v5 protocol provided a new solution to such this problem in the Hadoop-distributed platform (HDP). In this paper, we suggest a credible scheme by adding one more level of protection and authentication security to the Kerberos v5 protocol by using a static knowledge-based authentication (SKBA). Where in the login and verification phase by using Kerberos protocol, the KDC will replay with a question to the user-side to check the actual presence of user which the user already answered this question in his registration phase. Our credible scheme is useful in case of capturing messages that enable an eavesdropper to get the ticket that allows getting access to the HDFS as well as to avoid the common attacks with less computation, communication and storage cost. The proposed scheme works seriously and strictly to ensure the registration by delivery of user information over an insecure network in a safe manner and store this information in the KDC-database to be used later for getting access with HDFS.

show abstract

Building a practical and reliable classifier for malware detection

Cited by 11 publications

References 10 publications

SOM-Guided Evolutionary Search for Solving MinMax Multiple-TSP

SOM-Guided Evolutionary Search for Solving MinMax Multiple-TSP

An Ensemble Cost-Sensitive One-Class Learning Framework for Malware Detection

Static Knowledge-Based Authentication Mechanism for Hadoop Distributed Platform using Kerberos

Contact Info

Product

Resources

About