الفهرس 
الغلافOnly 14 pages are availabe for public view
 |  | from | 120 |  |  |
| | | from | 120 | | |
Abstract
Summary
The innovation and growth in the usability of handheld devices is astonishing. There is the nightmare of getting a malware program through many malicious applications and games available on google play for free. Therefore, users require some computational capacity to execute profoundly complex effective algorithms for mobile intrusion detection discovery, which is impossible to be available on mobile devices or any handheld devices.
Therefore, the need for a powerful platform like cloud seems to be necessary to protect the user from threats and several security issues. Cloud computing has overwhelmed the world, as there are various cloud-based intrusion detection Systems (IDS) that can enhance both security and the mobile performance.
In this thesis, a study of iterative review to mobile malware techniques, classes and the techniques used for the detection of malware by using different systems of cloud-based intrusion detection is covered.
In this thesis, a proposed algorithm is presented for enhancing handheld devices security and improve their performance by using a proposed Cloud-Based Intrusion Detection System (CBIDS). There is three suggested methods for CBIDS such as Virus Total Public API, Falcon Sandbox Public API and CloudSploit Public API. Some of achieved goals are improving protection against zero-days malware that can attack the mobile devices under any condition, saving time of regularly maintaining, updating traditional antivirus software and Reach to a high rate of accuracy and detection rate by executing a complex intrusion detection algorithms into the cloud side which will coast large processing power in host side.
In this thesis, the choice is on the CTU-13 dataset which is one of the best datasets to evaluate the performance of previous methods; especially in network computer security it is really
Important to have good datasets, because the data in the networks is infinite, changing, varied and with a high concept drift. These issues force us to obtain good datasets to train, verify and test the algorithms.
In this thesis, accuracy and detection rate are one of evaluation factors for the previous methods. The experimental results indicate that VirusTotal Public API have better accuracy rate than Falcon Sandbox Public API and CloudSploit Public API as the average accuracy of VirusTotal API over the CTU-13 datasets is 91% while the average of accuracy of Falcon Sandbox Public API is 78.25% and CloudSploit Public API is 76.56%.
In this thesis, The experimental results indicate VirusTotal Public API have better detection rate than Falcon Sandbox Public API and CloudSploit Public API as the average detection of VirusTotal API over the CTU-13 datasets is 88.05% while the average of detection rate of Falcon Sandbox Public API is 74.63% and CloudSploit Public API is 74.27%.
In addition to the detection rate and accuracy improvement, there is evaluation of VirusTotal API performance from the ability side of maintaining relative energy consumption. There is an intention to work in the future to make this system act as intrusion prevention system.