DREBIN: Effective and Explainable Detection of Android Malware in Your Pocket

By Daniel Arp, Michael Spreitzenbarth, Malte Hubner, Hugo Gascón, Konrad Rieck. 2014

2,526 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Software, Privacy & Security, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Software

In Privacy & Security

In Signal Processing

Citations in the corpus

Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks (2019, methodology): “In the security space, DNNs are used for everything from malware classification [1], [2], to binary reverseengineering [3], [4] and network intrusion detection [5].”
When Does Machine Learning FAIL? Generalized Transferability for Evasion and Poisoning Attacks (2018, methodology): “The Drebin Android malware detector [2] uses a linear SVM classifier to predict”
On the (Statistical) Detection of Adversarial Examples (2017, methodology): “0 to 9 taking real values [17]. It is composed of 60;000 images, of which 10;000 form a test dataset. Each image has 28x28 pixels. DREBIN—This malware dataset contains 545;333 binary malware features [2]. To make adversarial example crafting faster, we apply dimensionality reduction, as 5 done by Gr”
DeepXplore: Automated Whitebox Testing of Deep Learning Systems (2017, methodology): “Drebin is a dataset [3, 48] that includes 129, 013 Android applications among which 123, 453 are benign and 5, 560 are malicious.”
Yes, Machine Learning Can Be More Secure! A Case Study on Android Malware Detection (2017, methodology): “Drebin also provides an interpretation of its decision, by highlighting the most suspicious (or benign) features that contributed to the decision [3].”
subgraph2vec: Learning Distributed Representations of Rooted Sub-graphs from Large Graphs (2016, background): “The figure illustrates APIdependency subgraphs from a well-known Android malware called DroidKungFu (DKF) [18].”
The Space of Transferable Adversarial Examples (2017, methodology): “To measure transferability of these subspaces, we experiment on datasets for which diverse model classes attain high accuracy: digit classification [14] and malware detection [1].”
Adversarial Examples for Malware Detection (2017, methodology): “Applying the attack, we are able to mislead our best performing malware detector (on the DREBIN dataset [2]) at rates higher than 63%.”
Significant Permission Identification for Machine-Learning-Based Android Malware Detection (2018, methodology): “benign apps from 310,926 benign apps, downloaded from Google play store in June 2013 [9], to carry out crossvalidation.”
Stealth attacks: An extended insight into the obfuscation effects on Android malware (2015, neutral): “Recently, an anti-malware system based on machine learning techniques (Drebin) has been proposed [37].”
When a Tree Falls: Using Diversity in Ensemble Classifiers to Identify Evasion in Malware Detectors (2016, methodology): “We analyze the use of introspection in an ensemble classifier to detect when the classifier provides unreliable results at classification time.”
Deep Ground Truth Analysis of Current Android Malware (2017, methodology): “Arp, D., Spreitzenbarth, M., Hubner, M., Gascon, H., Rieck, K.: Drebin: effective and explainable detection of android malware in your pocket.”
Contextual Weisfeiler-Lehman graph kernel for malware detection (2016, methodology): “D REBIN [4] provides a collection on 5,560 Android malware apps collected from 2010 to 2012.”
SourceFinder: Finding Malware Source-Code from Publicly Available Repositories (2020, background): “Second, several efforts maintain databases of malware binaries but without source code [2, 3].”