Permission-based malware detection mechanisms for smart phones

2014 ◽  
Author(s):  
Ming-Yang Su ◽  
Wen-Chuan Chang
Keyword(s):  
Malware Detection ◽  
Smart Phones ◽  
Detection Mechanisms

Multi-Pattern Matching Based Dynamic Malware Detection in Smart Phones

2019 ◽  
pp. 421-441
Author(s):  
V. S. Devi ◽  
S. Roopak ◽  
Tony Thomas ◽  
Md. Meraj Uddin
Keyword(s):  
Pattern Matching ◽  
Malware Detection ◽  
Smart Phones

A Hybrid Approach to Detect the Malicious Applications in Android-Based Smartphones Using Deep Learning

2021 ◽  
pp. 626-644
Author(s):  
Manokaran Newlin Rajkumar ◽  
Varadhan Venkatesa Kumar ◽  
Ramachandhiran Vijayabhasker
Keyword(s):  
Deep Learning ◽  
Mobile Application ◽  
Hybrid Approach ◽  
Malware Detection ◽  
Control Flow ◽  
Smart Phones ◽  
The People ◽  
Flow Information ◽  
Android Applications ◽  
Modern Era

This modern era of technological advancements facilitates the people to possess high-end smart phones with incredible features. With the increase in the number of mobile applications, we are witnessing the humongous increase in the malicious applications. Since most of the Android applications are available open source and used frequently in the smart phones, they are more vulnerable. Statistical and dynamical-based malware detection approaches are available to verify whether the mobile application is a genuine one, but only to a certain extent, as the level of mobile application scanning done by the said approaches are in general routine or a common, pre-specified pattern using the structure of control flow, information flow, API call, etc. A hybrid method based on deep learning methodology is proposed to identify the malicious applications in Android-based smart phones in this chapter, which embeds the possible merits of both the statistical-based malware detection approaches and dynamical-based malware detection approaches and minimizes the demerits of them.

A Hybrid Approach to Detect the Malicious Applications in Android-Based Smartphones Using Deep Learning

2020 ◽  
pp. 176-194
Author(s):  
Manokaran Newlin Rajkumar ◽  
Varadhan Venkatesa Kumar ◽  
Ramachandhiran Vijayabhasker
Keyword(s):  
Deep Learning ◽  
Mobile Application ◽  
Hybrid Approach ◽  
Malware Detection ◽  
Control Flow ◽  
Smart Phones ◽  
The People ◽  
Flow Information ◽  
Android Applications ◽  
Modern Era

This modern era of technological advancements facilitates the people to possess high-end smart phones with incredible features. With the increase in the number of mobile applications, we are witnessing the humongous increase in the malicious applications. Since most of the Android applications are available open source and used frequently in the smart phones, they are more vulnerable. Statistical and dynamical-based malware detection approaches are available to verify whether the mobile application is a genuine one, but only to a certain extent, as the level of mobile application scanning done by the said approaches are in general routine or a common, pre-specified pattern using the structure of control flow, information flow, API call, etc. A hybrid method based on deep learning methodology is proposed to identify the malicious applications in Android-based smart phones in this chapter, which embeds the possible merits of both the statistical-based malware detection approaches and dynamical-based malware detection approaches and minimizes the demerits of them.

Limitations of Current Anti-Virus Scanning Technologies

2011 ◽  
pp. 190-209 ◽  
Author(s):  
Srinivas Mukkamala
Keyword(s):  
Malware Detection ◽  
Application Programming Interface ◽  
General Technique ◽  
Commercial Grade ◽  
Original Table ◽  
Application Programming ◽  
Detection Mechanisms ◽  
Current Detection ◽  
Programming Interface ◽  
Multiple Attack

Malware has become more lethal by using multiple attack vectors to exploit both known and unknown vulnerabilities and can attack prescanned targets with lightning speed. In the future, it is important that the scanners are capable of detecting polymoraphic (obfuscated or variant) and metamorphic (mutated or evolved) versions of malware, however current scanning techniques for malware detection have serious limitations. Simple software obfuscation a general technique that is used to protect the software from reverse engineering techniques can circumvent the current detection mechanisms (anti-virus tools). In this chapter, we describe common attacks on anti-virus tools and a few obfuscation techniques applied to recent viruses that were used to thwart commercial grade anti-virus tools. Similarities among different malware and their variants are also presented in this chapter. The signature used in this method is the percentage of application programming interface (APIs) appearing in the malware type. The hypothesis is that mutants and variants will not stray far from the original. Table 5 shows serious limitations of commercial grade anti-virus scanners in detecting simple obfuscation attacks. Table 6 shows the percentages of similarity of a particular malware when compared to others. One important thing to note is that even the polymorphic ZMist uses the same set of APIs on all three variants.

scholarly journals Cryptojacking Malware Detection using the Bayesian Consensus Clustering with Large Iterative Multi-Tier Ensemble in the Cryptocurrency in the Cloud

2019 ◽  
Vol 8 (3) ◽  
pp. 4256-4264
Keyword(s):  
Malware Detection ◽  
Smart Phones ◽  
Consensus Clustering ◽  
Online Data ◽  
Virtual Currency ◽  
Malicious Software ◽  
Security Breaches ◽  
Major Threat ◽  
Digital Currency ◽  
Blockchain Technology

Virtual Currencies and cryptocurrency are a trending digital currency method which uses the Blockchain technology. Cryptocurrency is a digital method designed to exchange the asset between the users based on a powerful cryptography which ensures the transaction are safe and controllable. We have various legal areas identified while using the cryptocurrency, as being the virtual currency, the amount of assets used by the users increases rapidly. With the increase in the asset the security breaches are one of the key vulnerable areas to focus. Cryptocurrency mining malware or Cryptojacking remains a trending terminology which identifies the malicious software or malware developed to use the data from the smart phones and computers. The major threat of the Cryptojacking is cryptocurrency mining without user’s approval. This article implemented based on our CCEC Framework method published for Malware detection in SMS’s for the Smartphone users. The article explains about how the Malware detected using the CCEC Framework. Malwares created in various format so identifying the Malware takes time before which user assets remains vulnerable. So, the proposed method ensures we have a reduction in time by using various online data sources to identify the Cryptojacking malware.

Sign in / Sign up

Export Citation Format

Share Document