On automatically detecting similar Android apps
The DOI matches its Crossref record; 44 of the 44 references it cites were found in a registry or an index.
Abstract
Detecting similar applications is a challenging problem, since it implies that similar high-level features and their low-level implementations can be detected and matched automatically. We propose an approach for automatically detecting Closely reLated applications in ANdroid (CLANdroid) by relying on advanced Information Retrieval techniques and five semantic anchors: identifiers, Android APIs, intents, permissions, and sensors. To evaluate CLANdroid we created a benchmark consisting of 14,450 apps along with information on similar apps provided by Google Play. We also compared effectiveness of different semantic anchors for detecting similar apps as perceived by 27 users. The results show that using Android-specific semantic anchors are useful for detecting similar Android apps across different categories. We also measured the impact of third-party libraries and obfuscated code when identifying similar Android apps, and our results suggest that there is significant difference in the accuracy when third-party libraries are excluded.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Indexing by latent semantic analysis
Deerwester, S., Dumais, S. T., Furnas, G. W., Landauer, T. K., & Harshman, R. (1990) · Journal of the American Society for Information Science · doi:10.1002/(sici)1097-4571(199009)41:6<391::aid-asi1>3.0.co;2-9 · Cited by 12,751
Handbook of Parametric and Nonparametric Statistical Procedures
(2004) · Technometrics · doi:10.1198/tech.2004.s209 · Cited by 4,661
Grissom, R. J., & Kim, J. J. (2012) · doi:10.4324/9780203803233 · Cited by 470 · cited 2×
“We followed the guidelines in [27] to interpret the effect size values: negligible for |d| < 0.”
MethodGPLAG: detection of software plagiarism by program dependence graph analysis
Liu, C., Chen, C., Han, J., & Yu, P. S. (2006) · Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/1150402.1150522 · Cited by 422
Checking app behavior against app descriptions
Gorla, A., Tavecchia, I., Gross, F., & Zeller, A. (2014) · Proceedings of the 36th International Conference on Software Engineering · doi:10.1145/2568225.2568276 · Cited by 397 · cited 2×
“[55] applies Latent Dirichlet Allocation on the descriptions of over 32K applications; the k-means algorithm is then used to cluster the apps (by using the topics generated with LDA) and, thus, provide the ability to identify”
BackgroundMethodEffect Sizes for Research: Univariate and Multivariate Applications
Grissom, R. J., & Kim, J. J. (2005) · Cited by 372
Hipikat: recommending pertinent software development artifacts
Čubranić, D., & Murphy, G. C. (2003) · doi:10.5555/776816.776866 · Cited by 317
Portfolio: finding relevant functions and their usage
McMillan, C., Grechanik, M., Poshyvanyk, D., Xie, Q., & Fu, C. (2011) · Proceedings of the 33rd International Conference on Software Engineering · doi:10.1145/1985793.1985809 · Cited by 313 · cited 1×
“[58] Finding relevant functions Function call graph D > 18K NA FB Thung et al.”
BackgroundSelf-citationAchieving accuracy and scalability simultaneously in detecting application clones on Android markets
Chen, K., Liu, P., & Zhang, Y. (2014) · Proceedings of the 36th International Conference on Software Engineering · doi:10.1145/2568225.2568286 · Cited by 287 · cited 3×
“[17] detect similar apps by comparing centroids created from dependency graphs at method level.”
BackgroundMethodAPI change and fault proneness: a threat to the success of Android apps
Linares-Vásquez, M., Bavota, G., Bernal-Cárdenas, C., Di Penta, M., Oliveto, R., & Poshyvanyk, D. (2013) · Proceedings of the 2013 9th Joint Meeting on Foundations of Software Engineering · doi:10.1145/2491411.2491428 · Cited by 259
Self-citation
Research works printed but not linked: 3
- 0, Sourceforge
- crussell, 2013, Scalable semantics-based detection of similar android applications, ESORICS'13
- minelli, 2013, Software analyticsfor mobile applications Insights and lessons learned
Cited by
LibD: Scalable and Precise Third-Party Library Detection in Android Markets
Li, M., Wang, W., Wang, P., Wang, S., Wu, D., Liu, J., Xue, R., & Huo, W. (2017) · 2017 IEEE/ACM 39th International Conference on Software Engineering (ICSE) · doi:10.1109/icse.2017.38 · Cited by 179
“To distinguish app-specific classes from third-party-library classes, V´asquez et al. [37], [38] extracted the package name (i.e., main package) from AndroidManifest.xml for an app.”
BackgroundDeep learning similarities from different representations of source code
Tufano, M., Watson, C., Bavota, G., Di Penta, M., White, M., & Poshyvanyk, D. (2018) · Proceedings of the 15th International Conference on Mining Software Repositories · doi:10.1145/3196398.3196431 · Cited by 158
“are used as features in approaches for identifying similar applications [47, 69], and AST pattern similarities are used to enable clone detection and refactoring [26, 33, 50].”
MethodSelf-citationRebooting Research on Detecting Repackaged Android Apps: Literature Review and Benchmark
Li, L., Bissyandé, T. F., & Klein, J. (2019) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2019.2901679 · Cited by 122
“Details in Table 3 show that no approach addresses all challenges, with Market-scale constraints being the least tackled in the [36] Symptom discovery string offset order CodeMatch [19] Similarity Comparison code fuzzy hash FUIDroid [22] Similarity Comparison layout tree APPraiser [23] Similarity Comparison resource fi…”
InfluentialAppFlow: using machine learning to synthesize robust, reusable UI tests
Hu, G., Zhu, L., & Yang, J. (2018) · ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) · doi:10.1145/3236024.3236055 · Cited by 97
“Previous works [15, 48, 51, 65, 74, 77, 81, 83, 85, 89, 90] learn useful features from codes for code completion, clone detection, bug finding, similar app detection, etc.”
BackgroundDetecting third-party libraries in Android applications with high precision and recall
Zhang, Y., Dai, J., Zhang, X., Huang, S., Yang, Z., Yang, M., & Chen, H. (2018) · IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER) · doi:10.1109/saner.2018.8330204 · Cited by 82
“Since Android apps are mostly released in binary format, existing work [38], [41] based on source code-level similarity analysis is not applicable.”
BackgroundClustering Mobile Apps Based on Mined Textual Features
Al-Subaihin, A. A., Sarro, F., Black, S., Capra, L., Harman, M., Jia, Y., & Zhang, Y. (2016) · Proceedings of the ... ACM-IEEE International Symposium on Empirical Software Engineering and Measurement/International Symposium on Empirical Software Engineering and Measurement · doi:10.1145/2961111.2962600 · Cited by 85
“Expanding on that, Linares-V´asquez et al. implemented a similarity detection technique that specifically leverages Android-specific app features excluding the app code itself such as intents, activities, API calls and sensor usage [26].”
MethodResearch on Third-Party Libraries in Android Apps: A Taxonomy and Systematic Literature Review
Zhan, X., Liu, T., Fan, L., Li, L., Chen, S., Luo, X., & Liu, Y. (2021) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2021.3114381 · Cited by 77
“Droid [110] showed that TPLs could affect the detection accuracy.”
BackgroundUnderstanding Third-Party Libraries in Mobile App Analysis
Wang, H., & Guo, Y. (2017) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1109/icse-c.2017.161 · Cited by 50
“The result of CLANDroid [8] suggested significant accuracy difference when TPLs are excluded.”
BackgroundA Large-Scale Empirical Study on Industrial Fake Apps
Tang, C., Chen, S., Fan, L., Xu, L., Liu, Y., Tang, Z., & Dou, L. (2019) · IEEE/ACM International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP) · doi:10.1109/icse-seip.2019.00028 · Cited by 45
“CLANdroid [30] detects similar apps through analyzing five semantic anchors (e.g., identifiers and Android APIs).”
User Perspectives of Mood-Monitoring Apps Available to Young People: Qualitative Content Analysis
Widnall, E., Grant, C., Wang, T., Cross, L., Velupillai, S. U., Roberts, A., Stewart, R. J., Simonoff, E. A., & Downs, J. M. (2020) · JMIR mhealth and uhealth · doi:10.2196/18140 · Cited by 55
“A full description of the API data collection methods can be found in Multimedia Appendix 1 [36,40-44].”
An automated approach to assess the similarity of GitHub repositories
Nguyen, P. T., Rocco, J. D., Rubei, R., & Ruscio, D. D. (2020) · Software Quality Journal · doi:10.1007/s11219-019-09483-0 · Cited by 38
“Being inspired by CLAN, Linares-V´asquez et al. develop CLANdroid for detecting similar Android applications with the assumption that similar apps share some semantic anchors (Linares-Vasquez et al. 2016).”
BackgroundEmpirical comparison of text-based mobile apps similarity measurement techniques
Al-Subaihin, A. A., Sarro, F., Black, S., & Capra, L. (2019) · Empirical Software Engineering · doi:10.1007/s10664-019-09726-5 · Cited by 37
“Linares-V´asquez et al. (2016) use the approach of McMillan et al. (2012) to automatically detect similar mobile apps.”
BackgroundMethodOn Locating Malicious Code in Piggybacked Android Apps
Li, L., Li, D., Bissyandé, T. F., Klein, J., Cai, H., Lo, D., & Traon, Y. L. (2017) · Journal of Computer Science and Technology · doi:10.1007/s11390-017-1786-z · Cited by 30
“After reduction, pair-wise comparison is still necessary to infer similar malware families [43] .”
BackgroundTell them apart: distilling technology differences from crowd-scale comparison discussions
Huang, Y., Chen, C., Xing, Z., Tian, L., & Liu, Y. (2018) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1145/3238147.3238208 · Cited by 29
“Different methods has been adopted to mine similar artefacts ranging from high-level software [33, 43], mobile applications [19, 31], github projects[49] to low-level third-party libraries [11, 13, 42], APIs [22, 37], code snippets [41], or Q&A questions [18].”
MethodRepDroid: An Automated Tool for Android Application Repackaging Detection
Yue, S., Feng, W., Ma, J., Jiang, Y., Tao, X., Xu, C., & Lü, J. (2017) · IEEE International Conference on Program Comprehension (ICPC) · doi:10.1109/icpc.2017.16 · Cited by 27
“[31] propose an approach to detect similar apps in Android (CLANdroid) by”
MethodCrossSim: Exploiting Mutual Relationships to Detect Similar OSS Projects
Nguyen, P. T., Rocco, J. D., Rubei, R., & Ruscio, D. D. (2018) · Euromicro Conference on Software Engineering and Advanced Applications (SEAA) · doi:10.1109/seaa.2018.00069 · Cited by 30
“In summary, by reviewing other additional similarity metrics [4], [11], [12], [24] which cannot be presented here due to space limitation, we have seen that they normally deal with either low-level or high-level similarity.”
BackgroundREPERSP: Recommending Personalized Software Projects on GitHub
Xu, W., Sun, X., Hu, J., & Li, B. (2017) · IEEE International Conference on Software Maintenance (ICSM) · doi:10.1109/icsme.2017.20 · Cited by 25
“used semantic anchors to find similar apps [14].”
MethodLarge-Scale Third-Party Library Detection in Android Markets
Li, M., Wang, P., Wang, W., Wang, S., Wu, D., Liu, J., Xue, R., Huo, W., & Zou, W. (2020) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2018.2872958 · Cited by 26
“To distinguish app-specific classes from third-party-library classes, V (cid:2) asquez et al. [59], [60] extracted the package name (i.e., main package) from AndroidManifest. xml for an app.”
BackgroundAn Evolutionary Approach to Adapt Tests Across Mobile Apps
Mariani, L., Pezzè, M., Terragni, V., & Zuddas, D. (2021) · doi:10.1109/ast52587.2021.00016 · Cited by 26
“Indeed, browsing the Google Play Store reveals many Android apps that are semantically similar, albeit offering different graphics appearance, access permissions, side features, and user experience [16]–[18].”
BackgroundSimilarity-based analyses on software applications: A systematic literature review
Auch, M., Weber, M., Mandl, P., & Wolff, C. G. (2020) · Journal of Systems and Software · doi:10.1016/j.jss.2020.110669 · Cited by 27
Lascad : Language-agnostic software categorization and similar application detection
Altarawy, D., Shahin, H., Mohammed, A., & Meng, N. (2018) · Journal of Systems and Software · doi:10.1016/j.jss.2018.04.018 · Cited by 22
GitRanking: A ranking of GitHub topics for software classification using active sampling
Sas, C., Capiluppi, A., Sipio, C. D., Rocco, J. D., & Ruscio, D. D. (2023) · Software Practice and Experience · doi:10.1002/spe.3238 · Cited by 21
“In [31], the authors propose CLANdroid, a CLAN adaptation to the Android apps domain, and evaluate the solution on 14,450 Android apps.”
BackgroundAntipatterns in software classification taxonomies
Sas, C., & Capiluppi, A. (2022) · Journal of Systems and Software · doi:10.1016/j.jss.2022.111343 · Cited by 15
Exposed! A case study on the vulnerability-proneness of Google Play Apps
Sorbo, A. D., & Panichella, S. (2021) · Empirical Software Engineering · doi:10.1007/s10664-021-09978-0 · Cited by 12
“2017), and (ii) developers can use similar APIs for implementing similar app functionalities (Vásquez et al. 2016).”
BackgroundToward Optimal Selection of Information Retrieval Models for Software Engineering Tasks
Rahman, M. M., Chakraborty, S., Kaiser, G. E., & Ray, B. (2019) · IEEE International Working Conference on Source Code Analysis and Manipulation (SCAM) · doi:10.1109/scam.2019.00022 · Cited by 11
“Other available metadata has been used to find similar applications: collaborative tagging [19], GUI layout [20], API call intents, permissions, and sensors [21], project popularity [22], etc..”
MethodAppAuth: Authorship Attribution for Android App Clones
Xu, G., Zhang, C., Sun, B., Yang, X., Guo, Y., Li, C., & Wang, H. (2019) · IEEE Access · doi:10.1109/access.2019.2944684 · Cited by 8
“CLANdroid [47] automatically detect closely related Android apps by relying on advanced information retrieval techniques and five semantic anchors: identifiers, Android APIs, intents, permissions, and sensors.”
MethodDiffTech: a tool for differencing similar technologies from question-and-answer discussions
Wang, H., Chen, C., Xing, Z., & Grundy, J. (2020) · ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) · doi:10.1145/3368089.3417931 · Cited by 8
“Different methods have been adopted to mine similar artefacts ranging from high-level software [27], mobile applications [17, 25], github projects [20, 31] to low-level third-party libraries [8, 10], APIs [6, 14, 22, 28], or Q&A questions [7, 13, 16].”
MethodMulti-granular software annotation using file-level weak labelling
Sas, C., & Capiluppi, A. (2023) · Empirical Software Engineering · doi:10.1007/s10664-023-10423-7 · Cited by 8
“We will present the construct validity , internal validity , and external validity that we encountered during our study, and we discuss how we addressed them.”
DiffTech: Differencing Similar Technologies From Crowd-Scale Comparison Discussions
Wang, H., Chen, C., Xing, Z., & Grundy, J. (2021) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2021.3059885 · Cited by 7
DroidVisor: An Android secure application recommendation system
Rustgi, P., Fung, C., Rashidi, B., & McInnes, B. T. (2017) · IFIP/IEEE International Symposium on Integrated Network Management (IM) · doi:10.23919/inm.2017.7987440 · Cited by 6
“[7] proposed CLANdroid, an approach to automatically detect similar Android apps.”
BackgroundMethodObfuscation-Resilient Code Recognition in Android Apps
Feichtner, J., & Rabensteiner, C. (2019) · International Conference on Availability, Reliability and Security (ARES) · doi:10.1145/3339252.3339260 · Cited by 8
“Techniques for clone detection work on semantic and syntactic features of programs and measure the similarity of code based on tokens [11, 33], parsing trees [3, 6], or dependency graphs [9, 23, 24].”
MethodGraph Convolutional Network-Based Repository Recommendation System
Liao, Z., Cao, S., Li, B., Liu, S., Zhang, Y., & Yu, S. (2023) · Computer Modeling in Engineering & Sciences · doi:10.32604/cmes.2023.027287 · Cited by 4
“Inspired by the CLAN algorithm, Linares-Vásquez et al. [9] proposed a CLANdroid algorithm to detect similar Android repositories.”
MethodAlmrayat, S., Yousef, R., & Sharieh, A. (2019) · International Journal of Computer Applications · doi:10.5120/ijca2019919075 · Cited by 3
Repacked android application detection using image similarity
Khan, M. A. R., Tripathi, R. C., & Kumar, A. (2020) · Nexo Revista Científica · doi:10.5377/nexo.v33i01.10058 · Cited by 3
Bogomolov, E., Golubev, Y., Lobanov, A., Kovalenko, V., & Bryksin, T. (2020) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1145/3324884.3415291 · Cited by 3
“ars given by the same user in a short period of time and contents of the projects’ README files. The problem of detecting similar applications is also actively researched in the domain of mobile apps [11, 14, 19, 20]. The main difference from open source software projects is the data associated witheachapp.Forappsinap…”
Towards Accuracy in Similarity Analysis of Android Applications
Kishore, S., Kumar, R., & Rajan, S. P. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-05171-6_8 · Cited by 2
Code Between the Lines: Semantic Analysis of Android Applications
Feichtner, J., & Gruber, S. (2020) · IFIP advances in information and communication technology · doi:10.1007/978-3-030-58201-2_12 · Cited by 2
“CLANdroid [12], in contrast, aims to identify similar apps by defining semantic anchors that refer to sensor information, permissions, intents, and identifiers.”
BackgroundMobile privacy leakage detection and prevention : from technical solutions to user experience.
Alqahtani, S. I. (2019) · Surrey Research Insight Open Access (The University of Surrey) · doi:10.15126/thesis.00850605
“presented CLANdroid to help users find alternative mobile apps by comparing Android-specific semantic anchors such as API calls, intents, permissions and a few others [135].”
BackgroundIdentifying parasitic malware as outliers by code clustering
Li, H., Huang, J., Liang, B., Shi, W., Wu, Y.-F. B., & Bai, S. (2020) · Journal of Computer Security · doi:10.3233/jcs-191313
“Our investigation shows that, a lot of studies have demonstrated the adverse effect of third-party libraries on malware detection and choose to remove the libraries [9,10,15,22,27,31,52,55,58,65,67,69, 70,77,85,89,91–93].”
Alves, N. D. C., Pereira, M. A., & von Wangenheim, C. G. (2021) · Anais do Workshop sobre Educação em Computação (WEI) · doi:10.5753/wei.2021.15913
RepkHunter: Obfuscation-Resilient Detection for Repackaged Mobile Applications
Jin, L., Zhang, K., Gao, Y. C., & Dong, W. (2026) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2026.3675510
“Numerous approaches have been proposed to detect repack-aged apps [2], [36], [43], [51], [53], [56], [57], [60].”
Influential
Metadata
- Authors
- Linares-Vasquez, M., Holtzhauer, A., & Poshyvanyk, D.
- Affiliations
- William & Mary (US)
- ORCID
- Poshyvanyk, Denys
- Venue
- 2016 IEEE 24th International Conference on Program Comprehension (ICPC)
- Publisher
- IEEE
- Published
- 2016-05
- Volume
- 2016
- Pages
- 1-10
- OpenAlex
- W2470924201
- Cited by
- 43
- References
- 44
- Citations by year
- 2026: 1 · 2023: 3 · 2022: 2 · 2021: 5 · 2020: 10 · 2019: 8 · 2018: 7 · 2017: 6 · 2016: 1
- FWCI
- 6.23
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Conference on Program Comprehension (ICPC) (publishedVersion)
- IEEE Conference Proceedings
- Topics
- Physical Sciences › Computer Science › Information Systems › Software Engineering Research
- Physical Sciences › Computer Science › Software › Advanced Malware Detection Techniques
- Physical Sciences › Computer Science › Information Systems › Mobile and Web Applications
- Keywords
- Android application, semantic anchors, Android API, intention, permission, sensors, information retrieval, third-party libraries, obfuscated code
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.