Juxtapp: A Scalable System for Detecting Code Reuse among Android Applications

By Steve Hanna, Ling Huang, Edward XueJun Wu, Saung Li, Charles J. P. Chen, Dawn Song. 2012

260 citations recorded by the source corpus.

Subfields: Information Systems, 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 Information Systems

1. Battista Biggio
2. Fabio Roli
3. Michael Backes
4. Sven Bugiel
5. Erik Derr
6. Samuel Rota Bulò
7. Ignazio Pillai
8. Marcello Pelillo

In Software

1. Lorenzo Cavallaro
2. Michael Backes
3. Sven Bugiel
4. Erik Derr
5. Yue Duan
6. Konrad Rieck
7. Heng Yin
8. Peng Liu

In Signal Processing

1. Battista Biggio
2. Fabio Roli
3. Lorenzo Cavallaro
4. Konrad Rieck
5. Daniel Arp
6. Michael Backes
7. Nicholas Carlini
8. Giorgio Fumera

Citations in the corpus

• Is data clustering in adversarial settings secure? (2013, background): “1, it has been frequently exploited in security-sensitive tasks [4, 16, 23, 24].”
• Poisoning Complete-Linkage Hierarchical Clustering (2014, background): “, malware) such as computer viruses or worms [3, 4], and even identifying repackaged Android applications and Android mobile malware [5, 6].”
• CopperDroid: Automatic Reconstruction of Android Malware Behaviors (2015, background): “Similarly, DroidRanger [48] and JuxtApp [22] identify known mobile malware repackaged into other apps.”
• Stack Overflow Considered Harmful? The Impact of Copy&Paste on Android Application Security (2017, methodology): “their Jaccard similarity [38], [39] which describes the similarity ratio of two sets.”
• Semantics-Aware Android Malware Classification Using Weighted Contextual API Dependency Graphs (2014, methodology): “Juxtapp [19] performed feature hashing on the opcode sequence to detect malicious code reuse.”
• Reliable Third-Party Library Detection in Android and its Security Applications (2016, methodology): “Prior work computed the similarity between apps using code-based similarity techniques [5, 17, 48] or by extracting semantic features from program dependency graphs [6, 7].”
• Structural detection of android malware using embedded call graphs (2013, methodology): “[17] employ feature hashing on byte code sequences to measure code similarity.”
• A measurement study of google play (2014, methodology): “These approaches are computationally complex as they are based on application code analysis, either using pairwise comparisons [16, 13, 27, 42] or comparing applications to a subset of their closest neighbors [14, 41].”
• Static analysis of android apps: A systematic literature review (2017, methodology): “As an example, we exclude Juxtapp [31], a clone detection approach, from consideration since it simply takes opcode sequences for its static analysis.”
• Achieving accuracy and scalability simultaneously in detecting application clones on Android markets (2014, background): “Hash-based approaches are efficient to detect code fragments clones [53, 17].”
• The Evolution of Android Malware and Android Analysis Techniques (2017, methodology): “Feature-based analysis extracts and studies sets of features from de-compiled apps in order to enforce policies, understand API permissions, and detect code reuse through feature hashing (e.g., Juxtapp [Hanna et al. 2013]).”