A New Malware Detection System Using Machine Learning Techniques for API Call Sequences

Jerlin, M. Asha; Marimuthu, K.

doi:10.1080/19361610.2018.1387734

Cited by 60 publications

(15 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This algorithm doesn't require a separate adept training or preparation of datasets as it is ready precisely after we label the dataset. This method initially uses a trial that is needed for classification and then begins to calculate the distances between the samples [16]. After that, the K nearest neighbors which have the shortest distances are selected and used in the decision-making process.…”

Section: Methods Algorithmsmentioning

confidence: 99%

Emerging Machine Learning Techniques in Malware Detection and Analysis: A Comparative Analysis

Chintha¹,

Kumar²

2020

IJAR

View full text Add to dashboard Cite

New types of malware with unique characteristics are being created daily in legion. This exponential increase in malwareis creating a threat to the internet. From the past decade, various techniques of malware analysis and malware detection have been developed to prevent the efficacy of malware. However, due to the fast-growing numbers and complexities in malware, it is getting difficult to detect and analyze the malware manually. Because of the inefficiency in manual malware analysis, automated malware detection and analysis would be a better solution. Thus, malware analysis supported by machine learning became a required part of malware analysis. The automation used in learning patterns in malware can help in efficiently identifying the complexities. Malware Analysis with help the Machine learning would be more efficacious in terms of automation and memory usage. In this paper, we conducted a review of emerging various ML (Machine Learning) strategies used so far, in the field of malware analysis, to give a comprehensive view of the existing processes. We systemized them on various aspects like their objectives, machine learning algorithms used, information about the malware, etc. We also highlighted the existing problems in this particular field of study and tried to find multiple ways in which advancements can happen concerning the current trends being used.

show abstract

Section: Methods Algorithmsmentioning

confidence: 99%

Emerging Machine Learning Techniques in Malware Detection and Analysis: A Comparative Analysis

Chintha¹,

Kumar²

2020

IJAR

View full text Add to dashboard Cite

show abstract

“…They adopt botnet linked patterns of requested permissions as a feature to evaluate benign and malware apps. Jerlin et al [ 41 ] suggested a new approach to detect malware by using its Application Programmable Interfaces (APIs). They adopt upper and lower boundaries as one of its feature to detect malware from Android.…”

Section: Related Work and Overview Of Proposed Frameworkmentioning

confidence: 99%

FSDroid:- A feature selection technique to detect malware from Android using Machine Learning Techniques

Mahindru

Sangal

2021

Multimed Tools Appl

View full text Add to dashboard Cite

With the recognition of free apps, Android has become the most widely used smartphone operating system these days and it naturally invited cyber-criminals to build malwareinfected apps that can steal vital information from these devices. The most critical problem is to detect malware-infected apps and keep them out of Google play store. The vulnerability lies in the underlying permission model of Android apps. Consequently, it has become the responsibility of the app developers to precisely specify the permissions which are going to be demanded by the apps during their installation and execution time. In this study, we examine the permission-induced risk which begins by giving unnecessary permissions to these Android apps. The experimental work done in this research paper includes the development of an effective malware detection system which helps to determine and investigate the detective influence of numerous well-known and broadly used set of features for malware detection. To select best features from our collected features data set we implement ten distinct feature selection approaches. Further, we developed the malware detection model by utilizing LSSVM (Least Square Support Vector Machine) learning approach connected through three distinct kernel functions i.e., linear, radial basis and polynomial. Experiments were performed by using 2,00,000 distinct Android apps. Empirical result reveals that the model build by utilizing LSSVM with RBF (i.e., radial basis kernel function) named as FSdroid is able to detect 98.8% of malware when compared to distinct anti-virus scanners and also achieved 3% higher detection rate when compared to different frameworks or approaches proposed in the literature.

show abstract

“…Jerlin and Marimuthu proposed an efficient Rate‐based MDNBS (Multi‐Dimensional Naïve Bayes Classification) technique for malware classification using API call sequences. MDNBS is used to classify types of malware as worms, virus, Trojans, or normal.…”

Section: Related Workmentioning

confidence: 99%

Ransomware detection using machine learning algorithms

Bae

Lee

2019

Concurrency and Computation

View full text Add to dashboard Cite

Summary The number of ransomware variants has increased rapidly every year, and ransomware needs to be distinguished from the other types of malware to protect users' machines from ransomware‐based attacks. Ransomware is similar to other types of malware in some aspects, but other characteristics are clearly different. For example, ransomware generally conducts a large number of file‐related operations in a short period of time to lock or to encrypt files of a victim's machine. The signature‐based malware detection methods, which have difficulties to detect zero‐day ransomware, are not suitable to protect users' files against the attacks caused by risky unknown ransomware. Therefore, a new protection mechanism specialized for ransomware is needed, and the mechanism should focus on ransomware‐specific operations to distinguish ransomware from other types of malware as well as benign files. This paper proposes a ransomware detection method that can distinguish between ransomware and benign files as well as between ransomware and malware. The experimental results show that our proposed method can detect ransomware among malware and benign files.

show abstract

A New Malware Detection System Using Machine Learning Techniques for API Call Sequences

Cited by 60 publications

References 14 publications

Emerging Machine Learning Techniques in Malware Detection and Analysis: A Comparative Analysis

Emerging Machine Learning Techniques in Malware Detection and Analysis: A Comparative Analysis

FSDroid:- A feature selection technique to detect malware from Android using Machine Learning Techniques

Ransomware detection using machine learning algorithms

Contact Info

Product

Resources

About