Mobile-sandbox: having a deeper look into android applications

By Michael Spreitzenbarth, Felix C. Freiling, Florian Echtler, T. Schreck, Johannes Hoffmann. 2013

304 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Software, 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

1. Giorgio Giacinto
2. Davide Maiorca
3. Jun Zhang
4. Thorsten Holz
5. Rosli Bin Salleh
6. Junfeng Yang
7. Surya Nepal
8. Mourad Debbabi

In Software

1. Suman Sekhar Jana
2. Kexin Pei
3. Junfeng Yang
4. Yinzhi Cao
5. Thorsten Holz
6. Rosli Bin Salleh
7. Surya Nepal
8. Giorgio Giacinto

In Signal Processing

1. Giorgio Giacinto
2. Suman Sekhar Jana
3. Davide Maiorca
4. Kexin Pei
5. Shiqi Wang
6. Junfeng Yang
7. Battista Biggio
8. Justin Whitehouse

Citations in the corpus

• Efficient Formal Safety Analysis of Neural Networks (2018, methodology): “Currently, there is a total of 784,544 binary features extracted from each application according to 8 predefined categories [35].”
• DeepXplore: Automated Whitebox Testing of Deep Learning Systems (2017, background): “Drebin [7, 69] is a dataset with 129, 013 Android applications among which 123, 453 are benign and 5, 560 are malicious.”
• MalDozer: Automatic framework for android malware detection using deep learning (2018, methodology): “The dynamic analysis methods (Canfora et al., 2016) (Spreitzenbarth et al., 2013) (Wei et al., 2012), (Karbab et al., 2016b) aim to identify behavioral signature or behavioral anomaly of the running app.”
• A Survey of Android Malware Detection with Deep Neural Models (2020, methodology): “Furthermore, several traditional ML-based Android malware detectors such as TaintDroid [63], Andrubis [64], EnDroid [65], MARVIN [66], and Mobile-sandbox [67] were proposed to utilize the dynamic behavioral features.”
• The Evolution of Android Malware and Android Analysis Techniques (2017, methodology): “Alternatively, to increase code coverage, SmartDroid [Zheng et al. 2012], EvoDroid [Mahmood et al. 2014], and [Spreitzenbarth et al. 2013] use static analysis to find all possible activity paths before guiding the dynamic analysis through them.”
• Evaluating Analysis Tools for Android Apps: Status Quo and Robustness Against Obfuscation (2016, background): “Mobile-Sandbox [16] checks for malware, determines required permissions, and identifies possible entry points.”
• ANDRUBIS -- 1,000,000 Apps Later: A View on Current Android Malware Behaviors (2014, background): “Consequently, a significant amount of research has focused on analyzing and detecting Android malware, with numerous tools and services being proposed and operated by researchers [7]– [11] and security companies [12]–[14].”
• FeatureSmith: Automatically Engineering Features for Malware Detection by Mining the Security Literature (2016, methodology): “We collect the malware family names from both the Drebin dataset [8] and from a list of malware families [2] caught by the Mobile-Sandbox analysis platform [43].”