Skip to main content

Social-Guard: Detecting Scammers in Online Dating

Suhaib Al-Rousan ; Abdullah Abuhussein ; Faisal Alsubaei ; Ozkan Kahveci ; Hazem Farra ; Sajjan Shiva (2020) — 2020 IEEE International Conference on Electro Information Technology (EIT)

Citation activity

Total citations · Google Scholar
Unavailable
Average per calendar year
Citation count unavailable

Counts reflect Google Scholar’s coverage and do not measure research quality. Source, calculation and limitations

View Original Source (opens in a new tab)

DOI: 10.1109/eit48999.2020.9208268 (opens in a new tab)

Country:   Global
Tags:   Celebrity Photos, Facial Recognition, Fake Profiles, Reverse Image Search, Romance Scams, Scam Detection, Usable Security
What do these research terms mean?
Preprint
A manuscript shared before formal peer review and publication. Check whether a later published version is available.
Dataset
A collection of data or examples for others to inspect or reuse. It can appear in Library search and topic mapping, but RSRC does not use dataset records as evidence in Research Insights.
Dissertation or thesis
Research submitted for an academic degree. This describes its format, not its reliability.
Journal article
An article published in a journal. This label alone does not establish peer review, study quality, or how well the findings apply elsewhere.
Qualitative research
Examines experiences, meanings, or processes, often through interviews or observations. It can explain how something happens without estimating how common it is.
Quantitative research
Uses numerical measurements to describe patterns or test relationships. A relationship between two measurements does not by itself show that one causes the other.
Systematic review
Uses a planned, documented method to find and assess research addressing a question. Its conclusions still depend on the included studies and what the search covered.
Meta-analysis
Statistically combines results from multiple studies. Combining studies does not remove weaknesses in their design or make unlike populations interchangeable.
Not classified
This record has no recognized label in this filter. It does not mean the publication used no method, or that no research exists.

Definitions draw on DataCite resource types; Cochrane review methods; NLM: association and causation. RSRC’s dataset and classification rules are explained in our methodology.

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
                

            

                    

                
Source updates

                

                    No notice found at last check
                

            

                    

                
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:
                                    
                                
    • 
                                                    

                    
                                        

                

                            

                    
Source updates

                    

                    
No incoming update notice was found in the dated Crossref response. Coverage is incomplete, particularly for corrections and expressions of concern; this is not a guarantee that the source is valid or unchanged.


                                            
    
                                                            
  • 
                                    Last source-status attempt:
                                    
                                
    • 
                                                    

                    
                                        

                

                            

                    
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

            
Social-Guard: Detecting Scammers in Online Dating presents a tool designed to help users of online dating platforms identify potential scammers. The authors frame the problem as a safety and authenticity challenge on dating sites and propose an image- and evidence-based approach to support users in making safer interactions. The tool operates through two main indicators. First, the Celebrity Photo Indicator uses deep learning-based image analysis via AWS Rekognition and Google Vision to determine whether photos in a suspect profile belong to a celebrity, returning a confidence-based result. Second, the Photo Online Existence Indicator checks whether photos from a suspect profile exist elsewhere on the Internet, providing URLs where matching images were found when possible. The workflow requires the user to log into their dating platform through Social-Guard, paste the suspect profile link, and receive a dashboard-style output that summarizes the indicators and potential scam likelihood. The authors report an evaluation framework centered on cases involving celebrity photos and non-celebrity photos, including examples of true positives, false positives, true negatives, and false negatives. They discuss how the two indicators complement each other, with the second indicator aiding decision-making when the first yields uncertain results. The discussion also notes limitations related to facial recognition challenges, such as obfuscated or altered images, and acknowledges plans to expand indicators and platforms. The work positions Social-Guard as a tool to raise awareness and support safer user interactions on dating sites, rather than providing definitive determinations of fraud.

          

        
                  

            
Identified Gaps

            
Existing approaches either rely on trained data that may miss newly created fake profiles, focus on bot-created or cross-platform profiles, or use incomplete indicators. The paper identifies a lack of a user-facing means to verify suspect dating profiles against external image databases. Image-only indicators also cannot definitively establish that a profile owner is a scammer.

          

        
                  

            
Methods

            
The authors developed Social-Guard, a web-based prototype that extracts photos from a supplied dating-profile link. It uses AWS Rekognition to identify celebrity faces and Google Vision to locate matching images online, then displays indicators and URLs on a dashboard. Evaluation used author-created OkCupid fake profiles containing celebrity and non-celebrity images, including online and unpublished photos, and examined true/false positive and negative cases.

          

        
                  

            
Limitations

            
The authors assume profiles using celebrity photos are scams, although some users may use such images without intent to harm. Recently uploaded photos may not yet be indexed, producing false indications that they are absent online. Web information and URLs can be inaccurate or duplicated. Facial recognition can be affected by pose, facial obstruction, makeup, and appearance changes. The tool also requires a copyable profile link and is not publicly available.

          

        
                  

            
Future Work

            
Add further scam indicators to improve prediction and certainty, including API confidence scores and demographic consistency checks. Compare additional AI image and video analysis APIs. Develop a way for smartphone-app users to submit profile photos when profile links cannot be copied. Extend scammer-indicator research to classified-ad sites and forums.

          

              

    
    

        
Related Research Insights

        

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