| Campo Dublin Core | Valor | Língua |
|---|
| dc.contributor.advisor | Almeida, Rodrigo Bonifácio de | - |
| dc.contributor.author | Calassio, João Victor de Souza | - |
| dc.identifier.citation | CALASSIO, João Victor de Souza. The use of argument comparison to improve the performance of mining sandboxes for Android malware detection. 2023. 33 f., il. Trabalho de conclusão de curso (Bacharelado em Ciência da Computação) — Universidade de Brasília, Brasília, 2023. | pt_BR |
| dc.description | Trabalho de conclusão de curso (graduação) — Universidade de Brasília, Instituto de Ciências Exatas, Departamento de Ciência da Computação, 2023. | pt_BR |
| dc.rights | Acesso Aberto | pt_BR |
| dc.subject.keyword | Malware (Software) | pt_BR |
| dc.subject.keyword | Antivírus (Software) | pt_BR |
| dc.subject.keyword | Android (Recurso eletrônico) | pt_BR |
| dc.title | The use of argument comparison to improve the performance of mining sandboxes for Android malware detection | pt_BR |
| dc.type | Trabalho de Conclusão de Curso - Graduação - Bacharelado | pt_BR |
| dc.date.accessioned | 2023-10-06T14:07:19Z | - |
| dc.date.available | 2023-10-06T14:07:19Z | - |
| dc.date.submitted | 2023-07-25 | - |
| dc.identifier.uri | https://bdm.unb.br/handle/10483/36321 | - |
| dc.language.iso | Inglês | pt_BR |
| dc.rights.license | A concessão da licença deste item refere-se ao termo de autorização impresso assinado pelo autor que autoriza a Biblioteca Digital da Produção Intelectual Discente da Universidade de Brasília (BDM) a disponibilizar o trabalho de conclusão de curso por meio do sítio bdm.unb.br, com as seguintes condições: disponível sob Licença Creative Commons 4.0 International, que permite copiar, distribuir e transmitir o trabalho, desde que seja citado o autor e licenciante. Não permite o uso para fins comerciais nem a adaptação desta. | pt_BR |
| dc.description.abstract1 | The Android platform, with its extensive user base and popularity has become a prime
target for malware attacks. For that reason, researchers have been interested on malware
detection methods, including the mining sandboxes approach. This approach focuses
on repackaged apps, a type of attack that consists on modifying an existing app and
introducing malicious behavior on it, and is highly prevalent on the Android platform.
The mining sandboxes technique takes advantage of test case generation tools to monitor
an app’s runtime behavior and detect potential malicious intentions through behavioral
differences between different versions of apps. While the studies have shown promising
conclusions, with over 70% detection accuracy, there’s still a lot of room for improvement.
This study investigates how the performance of the mining sandboxes can be improved
by combining some previously proposed techniques (such as static analysis) with an ap-
proach that extends the behavioral differences detection by taking into consideration the
arguments passed to sensitive methods, and if the type of malware has any influence on
the detection effectiveness. This is done by evolving DroidXP, an existing research frame-
work for mining sandboxes, and evaluating its performance on a comprehensive dataset
of 1,707 pairs of apps. The results show that there’s an improvement of 14% on the mal-
ware detection accuracy, and that there’s a high influence of the type of malware on the
detection outcome. | pt_BR |
| Aparece na Coleção: | Ciência da Computação
|
