Malware Detection By Using Logistic Regression With Dynamic Analysis

Deepali Gupta

ISBN 10: 6200082642 / ISBN 13: 9786200082640

Verlag: LAP LAMBERT Academic Publishing, 2019

Beschreibung

nach der Bestellung gedruckt Neuware - Printed after ordering - Use of mobile phones for getting to the web has extended broadly, anyway paying little heed to basic advances in processor power and exchange speed, using PDAs for examining isn't equivalent to work region scrutinizing. Content constituents and page arrangements are used to perform static goals to decide vindictiveness in the page content space. The investigation way centers on building an enhanced framework to distinguish malignant destinations consistently by joining of Dynamic recognizable proof methodologies. In the continuous separated from utilizing since quite a while ago settled static methodologies recommended already the dynamic examination bases on API Calls Observation and Filtration and furthermore for each malware family a plan of precedents are recognized, every model addressed a changed watched variation of the first malware record. The present work additionally centers on examining the executable page contents for malevolent code identification for API calls present in the content. Exploratory outcomes demonstrate that the enhanced strategy performs superior to past methodology that centers on just static examination.

Bestandsnummer des Verkäufers 9786200082640

Bibliografische Details

• Titel: Malware Detection By Using Logistic Regression With Dynamic Analysis
• Verlag: LAP LAMBERT Academic Publishing
• Erscheinungsjahr: 2019
• Sprache: Englisch
• ISBN-10: 6200082642
• ISBN-13: 9786200082640
• Einband: Taschenbuch
• Zustand: Neu

Über diesen Titel

Inhaltsangabe

Use of mobile phones for getting to the web has extended broadly, anyway paying little heed to basic advances in processor power and exchange speed, using PDAs for examining isn't equivalent to work region scrutinizing. Content constituents and page arrangements are used to perform static goals to decide vindictiveness in the page content space. The investigation way centers on building an enhanced framework to distinguish malignant destinations consistently by joining of Dynamic recognizable proof methodologies. In the continuous separated from utilizing since quite a while ago settled static methodologies recommended already the dynamic examination bases on API Calls Observation and Filtration and furthermore for each malware family a plan of precedents are recognized, every model addressed a changed watched variation of the first malware record. The present work additionally centers on examining the executable page contents for malevolent code identification for API calls present in the content. Exploratory outcomes demonstrate that the enhanced strategy performs superior to past methodology that centers on just static examination.