Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

MALDI-TOF Mass Spectrometry

MALDI-TOF Mass Spectrometry

Mass spectrometry is a powerful characterization technique that can identify and separate a wide variety of compounds ranging from chemical to biological entities, based on their mass-to-charge ratio (m/z). The instruments that allow this detection, known as mass spectrometers, have three components: an ion source, a mass analyzer, and a detector. These spectrometers differ based on the nature of their ion source and analyzers.
Matrix-assisted laser desorption ionization (MALDI) is a commonly...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Research on MOOCs course recommendation system based on hybrid attention mechanism in frequency and time domain.

PloS one·2025

Same author

Exploration of a Novel Electric-Fuse Device with a Simple Structure of Ni Metal on a SiO<sub>2</sub> Dielectric for Electrostatic Discharge Protection under a Human Body Model.

Micromachines·2024

Same author

Failure Mode and Effects Analysis on the Air System of an Aero Turbofan Engine Using the Gaussian Model and Evidence Theory.

Entropy (Basel, Switzerland)·2023

Same author

Uncertainty Management in Assessment of FMEA Expert Based on Negation Information and Belief Entropy.

Entropy (Basel, Switzerland)·2023

Same author

A New Reliability Coefficient Using Betting Commitment Evidence Distance in Dempster-Shafer Evidence Theory for Uncertain Information Fusion.

Entropy (Basel, Switzerland)·2023

Same author

Measuring Uncertainty in the Negation Evidence for Multi-Source Information Fusion.

Entropy (Basel, Switzerland)·2022

Search research articles

Related Experiment Video

Updated: Dec 9, 2025

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

A detection method for android application security based on TF-IDF and machine learning.

Hongli Yuan¹, Yongchuan Tang², Wenjuan Sun^1,3

¹Institute of information engineering, Anhui Xinhua University, Hefei, Anhui, China.

|September 11, 2020

Summary

This study introduces a novel static analysis method using Term Frequency-Inverse Document Frequency (TF-IDF) and machine learning to detect Android malware. The approach achieves high accuracy in identifying malicious apps and malware families, outperforming existing methods.

More Related Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Design and Analysis for Fall Detection System Simplification

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

Related Experiment Videos

Last Updated: Dec 9, 2025

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Design and Analysis for Fall Detection System Simplification

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

Area of Science:

Computer Science
Cybersecurity
Machine Learning

Background:

The proliferation of third-party Android app markets necessitates robust malware detection.
Existing detection methods struggle with evolving malware and system updates, leading to increased complexity and computational cost.
Android app permissions are critical for security, but their effective utilization in detection remains a challenge.

Purpose of the Study:

To propose a novel static detection method for Android malware leveraging TF-IDF and machine learning.
To develop a system that efficiently extracts and analyzes app permissions for security assessment.
To evaluate the proposed method's effectiveness against known and unknown Android malware and malware families.

Main Methods:

Static analysis to extract system permissions from Android application package (Apk) manifest files.
Application of Term Frequency-Inverse Document Frequency (TF-IDF) to calculate permission values (PV) and app sensitivity (SVOA).
Machine learning models trained and tested using SVOA and the count of used permissions on a large dataset of benign and malicious apps.

Main Results:

The proposed method achieved up to 99.5% accuracy for general malware detection and 99.6% for malware families detection.
The system demonstrated a rapid learning and training time of only 0.05s.
Detection accuracy for unknown/new samples reached 92.71%, indicating strong generalization capabilities.
Analysis revealed that relying solely on dangerous permissions or their count is insufficient for accurate classification.

Conclusions:

The TF-IDF and machine learning-based static analysis method offers a highly effective and efficient solution for Android malware detection.
The approach provides superior performance compared to existing state-of-the-art methods in identifying both known and novel threats.
This technique addresses the limitations of traditional methods by offering high accuracy with low computational overhead.