Side channel attack on mobile devices using machine learning
This report mainly highlights on what the author has done to explore the current avenues of side channel attacks on mobile devices through the use of a smartwatch. Firstly , existing side channel attacks methods that are implemented on a smartphone are discussed . These methods include methods that...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
2019
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/78333 |
| _version_ | 1824455025766694912 |
|---|---|
| author | Muhammad Jazeel Meerasah |
| author2 | Seow Chee Kiat |
| author_facet | Seow Chee Kiat Muhammad Jazeel Meerasah |
| author_sort | Muhammad Jazeel Meerasah |
| collection | NTU |
| description | This report mainly highlights on what the author has done to explore the current avenues of side channel attacks on mobile devices through the use of a smartwatch. Firstly , existing side channel attacks methods that are implemented on a smartphone are discussed . These methods include methods that make use of a smartwatch and other means of attacks. Secondly , the existing smartwatch Attack method was studied, and analyses based on what has been done so far in the past project . The goal is then set to understand how the Attack on the smartwatch is conducted , followed by coming up with any improvements to the existing algorithm or information. Next , multiple features are combined for different usage patterns of the individual users , so as to not create a separate model to cater to different users , which would then be not as effective anymore as a model . Secondly , a much larger dataset is also used to compare how the model fairs compared to the past project that was done. Supervised learning model, Support Vector Machine(SVM) is used to train the model using the improved dataset . These are some of the improvements that would be worked on in this report. Lastly , it is concluded that the improved method of attack works and is then considered for future works . |
| first_indexed | 2025-02-19T03:31:39Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/78333 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2025-02-19T03:31:39Z |
| publishDate | 2019 |
| record_format | dspace |
| spelling | ntu-10356/783332023-07-07T16:07:31Z Side channel attack on mobile devices using machine learning Muhammad Jazeel Meerasah Seow Chee Kiat School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering This report mainly highlights on what the author has done to explore the current avenues of side channel attacks on mobile devices through the use of a smartwatch. Firstly , existing side channel attacks methods that are implemented on a smartphone are discussed . These methods include methods that make use of a smartwatch and other means of attacks. Secondly , the existing smartwatch Attack method was studied, and analyses based on what has been done so far in the past project . The goal is then set to understand how the Attack on the smartwatch is conducted , followed by coming up with any improvements to the existing algorithm or information. Next , multiple features are combined for different usage patterns of the individual users , so as to not create a separate model to cater to different users , which would then be not as effective anymore as a model . Secondly , a much larger dataset is also used to compare how the model fairs compared to the past project that was done. Supervised learning model, Support Vector Machine(SVM) is used to train the model using the improved dataset . These are some of the improvements that would be worked on in this report. Lastly , it is concluded that the improved method of attack works and is then considered for future works . Bachelor of Engineering (Information Engineering and Media) 2019-06-18T07:03:56Z 2019-06-18T07:03:56Z 2019 Final Year Project (FYP) http://hdl.handle.net/10356/78333 en Nanyang Technological University 70 p. application/pdf |
| spellingShingle | DRNTU::Engineering::Electrical and electronic engineering Muhammad Jazeel Meerasah Side channel attack on mobile devices using machine learning |
| title | Side channel attack on mobile devices using machine learning |
| title_full | Side channel attack on mobile devices using machine learning |
| title_fullStr | Side channel attack on mobile devices using machine learning |
| title_full_unstemmed | Side channel attack on mobile devices using machine learning |
| title_short | Side channel attack on mobile devices using machine learning |
| title_sort | side channel attack on mobile devices using machine learning |
| topic | DRNTU::Engineering::Electrical and electronic engineering |
| url | http://hdl.handle.net/10356/78333 |
| work_keys_str_mv | AT muhammadjazeelmeerasah sidechannelattackonmobiledevicesusingmachinelearning |