Data

Tools

Indexes

Applications

Experiments

Open Source Science

asap

https://github.com/catarinaacsilva/asap

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (6.1%) to scientific vocabulary
Last synced: 10 months ago · JSON representation ·

Repository

Basic Info
  • Host: GitHub
  • Owner: catarinaacsilva
  • License: mit
  • Language: Jupyter Notebook
  • Default Branch: main
  • Size: 65.3 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 3
Created about 2 years ago · Last pushed over 1 year ago
Metadata Files
Readme License Citation

README.md

ASAP: A Dynamic & Proactive Approach for Android Security Analysis and Privacy

The main objective of this work is to identify which mobile applications violate user privacy, through the analysis of the requested permissions for execution.

We selected two datasets with the android applications permissions: Android Permission Dataset and Exodus Dataset. The class distribution between malicious and benign applications is really unbalanced.

Our proposed solution leverages an AutoEncoder trained to reproduce the Android permissions of benign applications. This means a well-trained AutoEncoder should accurately reconstruct benign applications, while malicious ones with different permission profiles will have a large reconstruction error. Therefore, a simple threshold algorithm can be used to separate benign from malicious applications. To establish a dynamic threshold level, we employ a variant of the ISODATA thresholding method that utilizes the median instead of the average. This approach is more robust for skewed reconstruction error distributions.

Authors

License

This project is licensed under the MIT License - see the LICENSE file for details.

Owner

  • Name: Catarina Silva
  • Login: catarinaacsilva
  • Kind: user
  • Location: Portugal
  • Company: IT Aveiro | UA

Ph.D student | Computer science | MAP-i

Citation (CITATION.cff) 

cff-version: 1.2.0
title: ASAP - A Dynamic & Proactive Approach for Android Security Analysis and Privacy
message: >-
  If you use this software, please cite it using the
  metadata from this file.
type: software
authors:
  - given-names: Catarina
    family-names: Silva
    email: c.alexandracorreia@ua.pt
    affiliation: Universidade de Aveiro
    orcid: 'https://orcid.org/0000-0002-7969-8813'
  - given-names: João
    family-names: Felisberto
    email: joaofelisberto@ua.pt
    affiliation: Universidade de Aveiro
  - given-names: João Paulo
    family-names: Barraca
    email: jpbarraca@ua.pt
    affiliation: Universidade de Aveiro
    orcid: 'https://orcid.org/0000-0002-5029-6191'
identifiers:
  - type: doi
    value: 10.5281/zenodo.10951599
repository-code: 'https://github.com/catarinaacsilva/ASAP'
url: 'https://github.com/catarinaacsilva/ASAP'
license: MIT
version: 0.1
date-released: '2024-04-10'

GitHub Events

Total
  • Push event: 6
  • Create event: 1
Last Year
  • Push event: 6
  • Create event: 1

Dependencies

requirements.txt pypi
  • imbalanced-learn >=0.12.2
  • ipywidgets >=8.1.2
  • jupyterlab >=4.1.6
  • matplotlib >=3.8.4
  • numpy >=1.26.4
  • polars >=0.20.19
  • pyarrow >=15.0.2
  • scikit-learn >=1.4.1.post1
  • tensorflow-cpu >=2.16.1
  • tqdm >=4.66.2