Skip to main content

An Explorative Study of Pig Butchering Scams

Acharya, Bhupendra ; Holz, Thorsten (2024) — arXiv (Cornell University)

View Original Source (opens in a new tab)

DOI: 10.48550/arxiv.2412.15423 (opens in a new tab)

Type:   Journal Article
Country:   Global
Tags:   Abuse Reports, AI-Enabled Fraud, Cross Platform Scams, Cryptocurrency Investment Fraud, Cryptocurrency Scams, Data Collection, Financial Losses, Investment Fraud, Law Enforcement, Measurement, Online Scams, Pig Butchering, Platform Policy, Prevention, Romance Scams, Scam Lifecycle, Social Engineering, Victim Experience, Victim Narratives
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:
                                    
                                
    • 
                                                            
  • 
                                    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 multi-source study collected social-media posts, abuse reports, and news cases in 2024, using language-model and NLP filtering followed by manual validation. Its final analytical material included 1,478 abuse reports, 2,570 victim narratives, 146 identified social-media victims, and 50 case studies, with estimated losses exceeding USD 521 million; a crowdsourced survey of roughly 584 users supplied comparison data. Among the 146 social-media victim accounts, 57% disclosed financial losses and 65% described the social-engineering techniques used against them. The broad collection provides several views of pig-butchering activity but not a population sample. Public-reporting and platform bias, possible classifier error, incomplete regional coverage, duplicated or missing cases, and privacy-limited detail constrain prevalence and causal inference.

          

        
                  

            
Identified Gaps

            
The study identifies a gap in understanding first-hand pig-butchering victim experiences across multiple platforms and the end-to-end scam lifecycle. Prior work largely treats romance, investment, and cryptocurrency scams in isolation and lacks a unified, multi-source, victim-centered lifecycle analysis. Data-sharing constraints and privacy protections limit access to scammer data, hindering comprehensive defense. A more diverse, longitudinal dataset spanning social media, abuse reports, and news, plus cross-platform tracking of scammer engagement, is needed to support proactive detection and prevention.

          

        
                  

            
Methods

            
Data come from three sources—social media posts, abuse databases, and news articles—collected Mar–Aug 2024. We applied automated LLM- and NLP-assisted filtration plus manual validation to identify pig-butchering cases. The final dataset includes 1,478 abuse reports, 2,570 victim narratives, 146 victims, 50 case studies, and estimated losses over $521M. A crowd-sourced survey (n≈586) compares experiences with romance and other scams. The analysis covers scam lifecycle, engagement channels, and payment methods to support defenses.

          

        
                  

            
Limitations

            
Limitations include reliance on publicly available data, which introduces reporting and platform biases; potential misclassification from LLM-based filtering despite manual checks; incomplete coverage across platforms and regions; and privacy constraints that restrict granular victim data, hindering causal inferences about risk factors and effectiveness of defenses.

          

        
                  

            
Future Work

            
Future work should extend cross-platform lifecycle tracking of pig-butchering, build privacy-preserving shared datasets, and develop proactive detection and user-education interventions. Additional replication across languages and regions, standardized metrics, and platform collaboration are needed to evaluate defenses and policy options for reducing losses.

          

              

    
    

        
Related Research Insights

        

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