scholarly journals An Analysis of Android Malware Classification Services

Sensors ◽  
2021 ◽  
Vol 21 (16) ◽  
pp. 5671
Author(s):  
Mohammed Rashed ◽  
Guillermo Suarez-Tangil
Keyword(s):  
Extensive Study ◽  
Research Community ◽  
Automated Classification ◽  
Classification Methods ◽  
Android Malware ◽  
Prevalence Studies ◽  
Malware Classification ◽  
The Family ◽  
Key Players ◽  
Detection Coverage

The increasing number of Android malware forced antivirus (AV) companies to rely on automated classification techniques to determine the family and class of suspicious samples. The research community relies heavily on such labels to carry out prevalence studies of the threat ecosystem and to build datasets that are used to validate and benchmark novel detection and classification methods. In this work, we carry out an extensive study of the Android malware ecosystem by surveying white papers and reports from 6 key players in the industry, as well as 81 papers from 8 top security conferences, to understand how malware datasets are used by both. We, then, explore the limitations associated with the use of available malware classification services, namely VirusTotal (VT) engines, for determining the family of an Android sample. Using a dataset of 2.47 M Android malware samples, we find that the detection coverage of VT’s AVs is generally very low, that the percentage of samples flagged by any 2 AV engines does not go beyond 52%, and that common families between any pair of AV engines is at best 29%. We rely on clustering to determine the extent to which different AV engine pairs agree upon which samples belong to the same family (regardless of the actual family name) and find that there are discrepancies that can introduce noise in automatic label unification schemes. We also observe the usage of generic labels and inconsistencies within the labels of top AV engines, suggesting that their efforts are directed towards accurate detection rather than classification. Our results contribute to a better understanding of the limitations of using Android malware family labels as supplied by common AV engines.

Youth Development in Europe

2009 ◽  
Vol 14 (4) ◽  
pp. 372-375 ◽  
Author(s):  
Katariina Salmela-Aro ◽  
Ingrid Schoon
Keyword(s):  
Young People ◽  
Relationship Quality ◽  
Youth Development ◽  
Social Relationships ◽  
Transition To Adulthood ◽  
Cultural Context ◽  
Integrative Framework ◽  
Reciprocal Interactions ◽  
The Family ◽  
Key Players

A series of six papers on “Youth Development in Europe: Transitions and Identities” has now been published in the European Psychologist throughout 2008 and 2009. The papers aim to make a conceptual contribution to the increasingly important area of productive youth development by focusing on variations and changes in the transition to adulthood and emerging identities. The papers address different aspects of an integrative framework for the study of reciprocal multiple person-environment interactions shaping the pathways to adulthood in the contexts of the family, the school, and social relationships with peers and significant others. Interactions between these key players are shaped by their embeddedness in varied neighborhoods and communities, institutional regulations, and social policies, which in turn are influenced by the wider sociohistorical and cultural context. Young people are active agents, and their development is shaped through reciprocal interactions with these contexts; thus, the developing individual both influences and is influenced by those contexts. Relationship quality and engagement in interactions appears to be a fruitful avenue for a better understanding of how young people adjust to and tackle development to productive adulthood.

Towards Deep Learning-Based Approach for Detecting Android Malware

2021 ◽  
pp. 2193-2219
Author(s):  
Jarrett Booz ◽  
Josh McGiff ◽  
William G. Hatcher ◽  
Wei Yu ◽  
James Nguyen ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Learning Environment ◽  
Malware Detection ◽  
Extensive Study ◽  
Detection Accuracy ◽  
Android Malware ◽  
Android Malware Detection ◽  
Mobile Malware Detection ◽  
Optimal Settings

In this article, the authors implement a deep learning environment and fine-tune parameters to determine the optimal settings for the classification of Android malware from extracted permission data. By determining the optimal settings, the authors demonstrate the potential performance of a deep learning environment for Android malware detection. Specifically, an extensive study is conducted on various hyper-parameters to determine optimal configurations, and then a performance evaluation is carried out on those configurations to compare and maximize detection accuracy in our target networks. The results achieve a detection accuracy of approximately 95%, with an approximate F1 score of 93%. In addition, the evaluation is extended to include other machine learning frameworks, specifically comparing Microsoft Cognitive Toolkit (CNTK) and Theano with TensorFlow. The future needs are discussed in the realm of machine learning for mobile malware detection, including adversarial training, scalability, and the evaluation of additional data and features.

Research into psychosocial issues

2021 ◽  
pp. 1295-1311
Author(s):  
David W. Kissane ◽  
Christopher H. Grossman ◽  
Clare O’Callaghan
Keyword(s):  
Quality Of Life ◽  
Family Caregiving ◽  
Social Issues ◽  
Death And Dying ◽  
Extensive Study ◽  
Research Outcomes ◽  
The Family ◽  
The Many ◽  
Study Designs

Psychological, existential, spiritual, and social issues cause much suffering and deserve extensive study to understand these concerns more fully and to intervene more effectively. Themes that abound include communication, coping, ethics, the family, caregiving, quality of life, death and dying, psychiatric disorders, suffering, and the many expressions of distress. Many study designs are possible to explore these themes, often with complementary quantitative and qualitative components. This chapter summarizes the psychometric properties of many of the instruments that are commonly employed in such studies, and describes quantitative, qualitative, and mixed methods designs used. The goal is to strengthen research design and optimize research outcomes to benefit the discipline.

New Opportunities, the Brain Drain, and the Guptas

2019 ◽  
pp. 33-54
Author(s):  
Jennifer B. Saunders
Keyword(s):  
United States ◽  
Brain Drain ◽  
Extended Family ◽  
The United States ◽  
Social Community ◽  
The Family ◽  
Key Players ◽  
History Of ◽  
Race And Religion ◽  
The Brain

This chapter provides information about the significant contexts of the Hindu American community’s narrative performances. Reviewing reasons behind why people immigrate, it begins with general theories of immigration and then concentrates on the specific reasons why Indians left India during the period after 1947. The chapter then shifts its focus to the context in the United States as a receiving site for immigrants from India with particular attention to race and religion, two dominant themes in American immigration that have contributed to the Guptas’ experiences and the dynamics of their community-making activities. This leads to a discussion of the significance of religion for migrants in the United States before introducing the more specific religious context of the Guptas’ community. Finally, the chapter expands its lens to their transnational extended family with family trees, a description of their social community, and a specific history of key players in the family.

scholarly journals Malware Classification Using Simhash Encoding and PCA (MCSP)

Symmetry ◽  
2020 ◽  
Vol 12 (5) ◽  
pp. 830
Author(s):  
Young-Man Kwon ◽  
Jae-Ju An ◽  
Myung-Jae Lim ◽  
Seongsoo Cho ◽  
Won-Mo Gal
Keyword(s):  
Covariance Matrix ◽  
Computer Systems ◽  
Classification Methods ◽  
Imbalanced Dataset ◽  
Malware Classification ◽  
Maximum Accuracy ◽  
Average Accuracy ◽  
Executable File ◽  
Linear Transform ◽  
Malicious Program

Malware is any malicious program that can attack the security of other computer systems for various purposes. The threat of malware has significantly increased in recent years. To protect our computer systems, we need to analyze an executable file to decide whether it is malicious or not. In this paper, we propose two malware classification methods: malware classification using Simhash and PCA (MCSP), and malware classification using Simhash and linear transform (MCSLT). PCA uses the symmetrical covariance matrix. The former method combines Simhash encoding and PCA, and the latter combines Simhash encoding and linear transform layer. To verify the performance of our methods, we compared them with basic malware classification using Simhash and CNN (MCSC) using tanh and relu activation. We used a highly imbalanced dataset with 10,736 samples. As a result, our MCSP method showed the best performance with a maximum accuracy of 98.74% and an average accuracy of 98.59%. It showed an average F1 score of 99.2%. In addition, the MCSLT method showed better performance than MCSC in accuracy and F1 score.

scholarly journals MobiSentry: Towards Easy and Effective Detection of Android Malware on Smartphones

2018 ◽  
Vol 2018 ◽  
pp. 1-14 ◽  
Author(s):  
Bingfei Ren ◽  
Chuanchang Liu ◽  
Bo Cheng ◽  
Jie Guo ◽  
Junliang Chen
Keyword(s):  
State Of The Art ◽  
Classification Algorithms ◽  
Defense System ◽  
Android Malware ◽  
Malware Classification ◽  
Android Os ◽  
Comprehensive Performance ◽  
Supervised Classifiers ◽  
Expert Analysis ◽  
Time Overhead

Android platform is increasingly targeted by attackers due to its popularity and openness. Traditional defenses to malware are largely reliant on expert analysis to design the discriminative features manually, which are easy to bypass with the use of sophisticated detection avoidance techniques. Therefore, more effective and easy-to-use approaches for detection of Android malware are in demand. In this paper, we present MobiSentry, a novel lightweight defense system for malware classification and categorization on smartphones. Besides conventional static features such as permissions and API calls, MobiSentry also employs the N-gram features of operation codes (n-opcode). We present two comprehensive performance comparisons among several state-of-the-art classification algorithms with multiple evaluation metrics: (1) malware detection on 184,486 benign applications and 21,306 malware samples, and (2) malware categorization on DREBIN, the largest labeled Android malware datasets. We utilize the ensemble of these supervised classifiers to design MobiSentry, which outperforms several related approaches and gives a satisfying performance in the evaluation. Furthermore, we integrate MobiSentry with Android OS that enables smartphones with Android to extract features and to predict whether the application is benign or malicious. Experimental results on real smartphones show that users can easily and effectively protect their devices against malware through this system with a small run-time overhead.

Sign in / Sign up

Export Citation Format

Share Document