Skip to main content

Dating with Scambots: Understanding the Ecosystem of Fraudulent Dating Applications

Hu, Yangyu ; Wang, Haoyu ; Zhou, Yajin ; Guo, Yao ; Li, Li ; Luo, Bingxuan ; Xu, Fangren (2021) — IEEE Transactions on Dependable and Secure Computing

View Original Source (opens in a new tab)

DOI: 10.1109/tdsc.2019.2908939 (opens in a new tab)

Type:   Journal Article
Country:   China
Tags:   Android App Markets, App Ecosystem, Chatbots, Fake Dating Profiles, Fraudulent Dating Apps, Mobile Advertising, Premium Service Fraud, Ranking Fraud
Citation tools
Download RIS Download BibTeX 


              
              

            

          

        


      

      

    

        
Transparency

        
Evidence and review status

        
This page contains AI-generated content. No human content review or subject-matter-expert review is recorded.

    


    

                    

                
Source basis

                

                    Downloaded PDF
                

            

                    

                
AI-generated page content

                

                    Yes
                

            

                    

                
Automated checks

                

                    Passed
                

            

                    

                
Administrative approval

                

                    Yes
                

            

                    

                
Human content review

                

                    Not recorded
                

            

                    

                
Subject-matter-expert review

                

                    Not recorded
                

            

            


    

        
            How this was prepared
        
        

                            

                    
Source basis

                    

                    
RSRC downloaded and privately stored a copy of the paper for internal analysis. The PDF is not offered to viewers from this page.


                                            
    
                                                            
  • 
                                    PDF added to RSRC:
                                    
                                
    • 
                                                    

                    
                                        

                

                            

                    
AI-generated page content

                    

                    
AI-generated research notes displayed on this page: Synopsis, Identified gaps, Methods, Limitations, Future work. The paper itself is not described as AI-generated.


                                            
    
                                                            
  • 
                                    Document analysis recorded:
                                    
                                
    • 
                                                            
  • 
                                    Synopsis generation recorded:
                                    
                                
    • 
                                                            
  • 
                                    Page record updated:
                                    
                                
    • 
                                                    

                    
                                        

                

                            

                    
Automated checks

                    

                    
The current, source-bound synopsis passed the recorded versioned publication checks.


                                            
    
                                                            
  • 
                                    Checks completed:
                                    
                                
    • 
                                                    

                    
                                            

                            
                                View passed checks (3)
                            
                            
    
                                                                    
  • Length, completeness, repetition, refusal, boilerplate, and active-markup screening
    • 
                                                                    
  • Numerical claims checked against the available source text
    • 
                                                                    
  • English-source lexical grounding check
    • 
                                                            

                        

                                        

                

                            

                    
Administrative approval

                    

                    
An authenticated administrator approved the bibliographic record for public Library display. This is not a review of every research claim.


                                            
    
                                                            
  • 
                                    Approved for public display:
                                    
                                
    • 
                                                    

                    
                                        

                

                            

                    
Human content review

                    

                    
No human review is recorded for the AI-generated content displayed on this page.


                    
                                        

                

                            

                    
Subject-matter-expert review

                    

                    
RSRC has not recorded review of this content by a subject-matter or methods expert.


                    
                                        

                

                    

    


    

        Review-state definitions

        Found a possible error?
        Request a correction.
    



    



              

        
                  

            
Synopsis

            
This publication examines a distinct and previously underexplored class of mobile apps that pose as dating platforms but are designed to extract money from users through premium services. The authors set out to understand the ecosystem surrounding these fraudulent dating apps, including their aims, participants, and impact on victims. They frame the work around a three-phase approach to detecting such apps and characterizing their behavior by analyzing app metadata, static code, and user interaction patterns. The study finds that many accounts within these apps are not operated by real people but by chatbots that use predefined templates to seed conversations. The authors describe a business model in which multiple parties—developers, distributors, and publishers—collaborate to bring these apps to market and monetize them through in-app purchases. They also report on how these apps are promoted and distributed via app markets and advertising networks, and they discuss ways in which fake reviews and other ranking tricks are used to attract users. Based on their analysis, the authors argue for the need to develop more effectiveDetection mechanisms beyond traditional antivirus signals, given that existing engines frequently fail to flag these applications. The paper discusses limitations of the study and points to broader implications for policy, platform vetting, and regulation. It emphasizes that current approaches may miss these programs and calls for continued research into more robust detectors and vetting processes to protect users. Overall, the work provides a grounded, evidence-based look at fraudulent dating apps and the ecosystem that sustains them, while acknowledging areas where further validation and broader geographic coverage would strengthen understanding.

          

        
                  

            
Identified Gaps

            
The authors identify incomplete detection of fraudulent dating apps by current antivirus engines and a need for better automated detection and regulation. The study is concentrated in Chinese app markets, so the prevalence and operation of comparable apps elsewhere remain uncertain. Existing techniques also incompletely identify fake accounts and manipulated reviews.

          

        
                  

            
Methods

            
The study analyzed 2.5 million Android apps collected from Google Play and nine third-party markets between April and August 2017. It used keyword screening, static in-app-purchase analysis, resource/code-similarity clustering, and manual inspection to identify 967 fraudulent dating apps in 22 families. Researchers crawled profiles and network traffic, compared avatars, conducted a 22-app field study with paid subscriptions, analyzed publishers, reviews, advertising distribution, downloads, payments, revenue estimates, VirusTotal labels, and later app removals.

          

        
                  

            
Limitations

            
The detection pipeline may miss fraudulent apps because its keyword and in-app-purchase-library lists were incomplete. Avatar duplication provides only a lower-bound estimate of fake accounts and can miss more sophisticated profiles. Exact text matching for repeated reviews can miss semantically similar review fraud. The dataset was concentrated in Chinese markets and primarily targeted China, limiting generalization to other countries.

          

        
                  

            
Future Work

            
Develop more advanced fake-account detection using user-behavior approaches. Extend the crawler to collect apps from markets in other countries and languages. Develop automated or semi-automated detectors using the identified app characteristics, and improve app-market and advertising-network vetting to detect or block fraudulent dating apps.

          

              

    
    

        
Related Research Insights

        

            See how this publication connects to RSRC's living evidence syntheses through current citations and research-topic mapping.