Android Malware

Android malware detection is a critical area of cybersecurity research aiming to automatically identify malicious applications. Current research focuses on improving the accuracy and robustness of detection methods, employing various machine learning techniques including graph neural networks, support vector machines, and transformer-based models like BERT, often incorporating feature selection and data augmentation strategies to address challenges like obfuscation and adversarial attacks. These advancements are crucial for enhancing mobile security and protecting users from increasingly sophisticated malware threats, with ongoing efforts to improve model explainability and address issues of reproducibility and fairness in evaluation.

Papers

January 30, 2023

Investigating Feature and Model Importance in Android Malware Detection: An Implemented Survey and Experimental Comparison of ML-Based Methods
Ali Muzaffar, Hani Ragab Hassen, Hind Zantout, Michael A Lones
Machine Learning Model Random Forest Content Based Feature Malware Attack High Detection Android Malware Experimental Comparison Model Importance

November 23, 2022

A Dynamic Weighted Federated Learning for Android Malware Classification
Ayushi Chaudhuri, Arijit Nandi, Buddhadeb Pradhan
Federated Learning Federated Averaging Android Malware

November 20, 2022

Mask Off: Analytic-based Malware Detection By Transfer Learning and Model Personalization
Amirmohammad Pasdar, Young Choon Lee, Seok-Hee Hong
Deep Neural Network Transfer Learning Malware Detection Android Malware Model Personalization

October 25, 2022

Flexible Android Malware Detection Model based on Generative Adversarial Networks with Code Tensor
Zhao Yang, Fengyang Deng, Linxi Han
Generative Adversarial Network Malware Detection Android Malware Tensor Code

September 8, 2022

Suspicious and Anomaly Detection
Shubham Deshmukh, Favin Fernandes, Monali Ahire, Devarshi Borse, Amey Chavan
Anomaly Detection Unlabeled Anomaly CNN Architecture Android Malware Real Time Detection Suspicious Commenter

May 30, 2022

Level Up with RealAEs: Leveraging Domain Constraints in Feature Space to Strengthen Robustness of Android Malware Detection
Hamid Bostani, Zhengyu Zhao, Zhuoran Liu, Veelasha Moonsamy
Native Robustness Adversarial Example Feature Space Android Malware Real World Attack Domain Constraint

May 25, 2022

Towards a Fair Comparison and Realistic Evaluation Framework of Android Malware Detectors based on Static Analysis and Machine Learning
Borja Molina-Coronado, Usue Mori, Alexander Mendiburu, Jose Miguel-Alonso
Machine Learning Static Analysis Android Malware Fair Comparison

May 17, 2022

A two-steps approach to improve the performance of Android malware detectors
Nadia Daoudi, Kevin Allix, Tegawendé F. Bissyandé, Jacques Klein
System Performance Malware Detection Android Malware Two Step

April 12, 2022

Malceiver: Perceiver with Hierarchical and Multi-modal Features for Android Malware Detection
Niall McLaughlin
Malware Detection Multi Modal Feature Malware Classification Android Malware Malware Analysis

March 4, 2022

Adversarial Patterns: Building Robust Android Malware Classifiers
Dipkamal Bhusal, Nidhi Rastogi
Adversarial Attack Adversarial Learning Malware Detection Android Malware Adversarial Pattern Malware Classifier

February 28, 2022

MaMaDroid2.0 -- The Holes of Control Flow Graphs
Harel Berger, Chen Hajaj, Enrico Mariconti, Amit Dvir
Android Malware Evasion Attack Malicious Sample Control Flow Fine Hole

January 20, 2022

Android Malware Detection using Feature Ranking of Permissions
Muhammad Suleman Saleem, Jelena Mišić, Vojislav B. Mišić
Random Forest Malware Attack Android Malware Malware Family Random Forest Classifier Feature Ranking Agentive Permission

January 19, 2022

Graph Neural Network-based Android Malware Classification with Jumping Knowledge
Wai Weng Lo, Siamak Layeghy, Mohanad Sarhan, Marcus Gallagher, Marius Portmann
Graph Neural Network Graph Neural GNN Based Android Malware Call Graph

November 6, 2021

"How Does It Detect A Malicious App?" Explaining the Predictions of AI-based Android Malware Detector
Zhi Lu, Vrizlynn L. L. Thing
Human Prediction Artificial Intelligence Model Android Malware AI Based Model Agnostic Explanation

Android Malware

Papers

Investigating Feature and Model Importance in Android Malware Detection: An Implemented Survey and Experimental Comparison of ML-Based Methods

A Dynamic Weighted Federated Learning for Android Malware Classification

Mask Off: Analytic-based Malware Detection By Transfer Learning and Model Personalization

Flexible Android Malware Detection Model based on Generative Adversarial Networks with Code Tensor

Suspicious and Anomaly Detection

Level Up with RealAEs: Leveraging Domain Constraints in Feature Space to Strengthen Robustness of Android Malware Detection

Towards a Fair Comparison and Realistic Evaluation Framework of Android Malware Detectors based on Static Analysis and Machine Learning

A two-steps approach to improve the performance of Android malware detectors

Malceiver: Perceiver with Hierarchical and Multi-modal Features for Android Malware Detection

Adversarial Patterns: Building Robust Android Malware Classifiers

MaMaDroid2.0 -- The Holes of Control Flow Graphs

Android Malware Detection using Feature Ranking of Permissions

Graph Neural Network-based Android Malware Classification with Jumping Knowledge

"How Does It Detect A Malicious App?" Explaining the Predictions of AI-based Android Malware Detector