Computer and Network Security

The Android operating system has become the most popular operating system for smartphones and tablets leading to a rapid rise in malware. Sophisticated Android malware employ detection avoidance techniques in order to hide their malicious activities from analysis tools. These include a wide range of anti-emulator techniques, where the malware programs attempt to hide their malicious activities by detecting the emulator. For this reason, countermeasures against anti-emulation are becoming increasingly important in Android malware detection. Analysis and detection based on real devices can alleviate the problems of anti-emulation as well as improve the effectiveness of dynamic analysis. Hence, in this paper we present an investigation of machine learning based malware detection using dynamic analysis on real devices. A tool is implemented to automatically extract dynamic features from Android phones and through several experiments, a comparative analysis of emulator based vs. device based detection by means of several machine learning algorithms is undertaken. Our study shows that several features could be extracted more effectively from the on-device dynamic analysis compared to emulators. It was also found that approximately 24% more apps were successfully analysed on the phone. Furthermore, all of the studied machine learning based detection performed better when applied to features extracted from the on-device dynamic analysis.

Being a small country with a huge population Bangladesh is commonly known as an agriculture based nation. Per capita land in comparison to the number of people is very insignificant and hence the management of land system holds a vital role in the economic and social aspects of this country. Eventually the land management system of this country urges to grow into a very efficient system. Unfortunately the reality is lagging behind too far and the land management system of this country has gradually become a burdensome matter which is now entirely impotent to encounter the newly evolving land issues and problems. Majority of the conflicts and quarrels in rural as well as urban areas arise as a result of the inefficient and corrupted land systems which in turns often create a long term problem. Nevertheless, some researchers have tried to come up with a solution but none could make it work. The implement level tasks have remained unexplored in some way or other and consequently the land management system have failed to realize its goals. In a nutshell, the land management system is concerned with two major issue-land surveying and land management. Only eyeing to one issue neglecting to face the other one will not come up with a fruitful upshot. Out of this fact identified, the paper proposes a model land management system which offers both the solutions-GPS based land surveying and online land management encompassing an assortment of web based participatory services. We have also implemented our solution using some real life scenario and data and tried to face the real life complications and hitches.

A secure network depends in part on user authentication and regrettably the authentication systems currently in use are not completely safe. However, the user is not the only party that needs to be authenticated to ensure the security of transactions on the Internet. Existing OTP mechanism cannot guarantee reuse of user's account by an adversary, re-use stolen user's device which is used in the process of authentication, and non-repudiation. This paper proposed mechanism of multi factor for secure electronic authentication. It intends to authenticate both of user and mobile device and guarantee non-repudiation, integrity of OTP from obtaining it by an adversary. The proposal can guarantee the user’s credentials by ensuring the user’s authenticity of identity and checking that the mobile device is in the right hands before sending the OTP to the user. This would require each user having a unique phone number and a unique mobile device (unique International Mobile Equipment Identity (IMEI)), in addition to an ID card number. By leveraging existing communication infrastructures, the mechanism would be able to guarantee the safety of electronic authentication, and to confirm that it demonstrates excellence in non-repudiation, authenticate user and mobile device which are used in the process of authentication, certification strength and also in comparison and analysis through experimenting with existing OTP mechanisms.

https://sites.google.com/site/ijcsis/

Ecumenically, the fastest growing segment of Big Data is human biology-related data and the annual data creation is on the order of zetabytes. The implications are global across industries, of which the treatment of brain related illnesses and trauma could see the most significant and immediate effects. The next generation of health care IT and sensory devices are acquiring and storing massive amounts of patient related data. An innovative Brain-Computer Interface (BCI) for interactive 3D visualization is presented utilizing the Hadoop Ecosystem for data analysis and storage. The BCI is an implementation of Bayesian factor analysis algorithms that can distinguish distinct thought actions using magneto encephalographic (MEG) brain signals. We have collected data on five subjects yielding 90% positive performance in MEG mid- and post-movement activity. We describe a driver that substitutes the actions of the BCI as mouse button presses for real-time use in visual simulations. This process has been added into a flight visualization demonstration. By thinking left or right, the user experiences the aircraft turning in the chosen direction. The driver components of the BCI can be compiled into any software and substitute a user’s intent for specific keyboard strikes or mouse button presses. The BCI’s data analytics OPEN ACCESS Brain. Sci. 2015, 5 420 of a subject’s MEG brainwaves and flight visualization performance are stored and analyzed using the Hadoop Ecosystem as a quick retrieval data warehouse.
Keywords: brain-computer interface; massive data management; machine learning algorithms; magnetoencephalographic (MEG); electroencephalography (EEG); 3D visualization; Hadoop Ecosystem

The research in the domain of ransomware is rapidly emerging, and the application of machine learning algorithms in ransomware detection is one of the recent breakthroughs. In this research, we constructed an experimental platform using ransomware datasets to compare the performance of various machine learning algorithms such as Random Forest, Gradient Boosting Decision Tree (GBDT), Neural Network using Multilayer Perceptron as well as three types of Support Vector Machine (SVM) kernels in ransomware detection. Our experiment is based on a combination of different methodologies reported in the existing literature. We used complete executable files in our experiment, analyzed the opcodes and measures their frequencies. The objective of this research was to discover the algorithms that are highly suitable to develop models as well as systems for ransomware detection. Consequently, we identified that Random Forest, GBDT and SVM (Linear) have shown optimal results in detection of ransomware.

In the era of information technology and connected world, detecting malware has been a major security concern for individuals, companies and even for states. The New generation of malware samples upgraded with advanced protection mechanism such as packing, and obfuscation frustrate anti-virus solutions. API call analysis is used to identify suspicious malicious behavior thanks to its description capability of a software functionality. In this paper, we propose an effective and efficient malware detection method that uses sequential pattern mining algorithm to discover representative and discriminative API call patterns. Then, we apply three machine learning algorithms to classify malware samples. Based on the experimental results, the proposed method assures favorable results with 0.999 F-measure on a dataset including 8152 malware samples belonging to 16 families and 523 benign samples.

Abstrak Linux dapat dikatakan biasa digunakan untuk melakukan kegiatan pengujian penetrasi pada suatu sistem. Pada proyek akhir ini akan diperkenalkan cara baru untuk melakukan hacking atau pengujian penetrasi pada sebuah sistem dengan menggunakan smartphone. Smartphone yang biasa menggunakan system operasi android tersebut akan di flash ulang sehingga dapat menggunakan sistem operasi yang hampir sama dengan Linux yaitu Kali Net Hunter. Kemudian jika Kali Net Hunter telah ter-install pada smartphone tersebut akan dilakukan pengujian dengan menggunakan HID keyboard attack, yaitu penyerangan untuk merekam keylogger pada sebuah browser. Penyerangan dilakukan dengan cara menghubungkan smartphone dengan laptop korban dengan kabel USB dan menanamkan exploit pada laptop korban, kemudian penyerangan dilakukan dengan menggunakan metasploit. Ketika korban mengetikkan username dan password saat melakukan login maka akan terekam. Kata Kunci: Kali Net Hunter, HID Keyboard Attack, Metasploit, penetration Abstract Linux also can be used to perform penetration testing on a system. Remember if a hacker or someone who wants to doing a penetration test require needs a laptop to do such activities on a site adjacent to the target will give rise to suspicion, then that is considered less effective way to conduct such activities, so there is this final project will be introduced a new way to perform penetration testing or hacking on a system by using smartphone. The usual Smartphone using the android operating system in flash reset so can use almost the same operating system with Linux i.e. Kali Net Hunter. Then if the Kali Net Hunter has been installed on a smartphone will be testing using the HID keyboard attack, that assault to record a keylogger on a browser. The assault was conducted by way of a connecting victims with laptop with smartphone USB cable and embed code on the victim's laptop, then attacks is done using metasploit. When victims type in the username and password during login it will be recorded.