Skip to main content

An Explorative Study of Pig Butchering Scams

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

DOI: 10.48550/arxiv.2412.15423
Type:   Journal Article
Country:   Global
Tags:   pig-butchering, romance scams, investment fraud, social engineering, cryptocurrency scams, online scams, abuse reports, scam lifecycle, victim experience, law enforcement, platform policy, AI misuse, prevention, measurement, data collection, romance fraud, cryptocurrency investment fraud, victim narratives, financial losses, cross-platform scams

Synopsis (AI-Generated)

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 (AI-Generated)

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 (AI-Generated)

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 (AI-Generated)

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 (AI-Generated)

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.

AI-Generated Content Notice

The synopsis and research notes on this page were generated with AI from available publication information and, when available, the uploaded paper text. They may contain errors, omissions, or interpretation issues. Readers should follow the DOI or source link, review the original publication, and make their own judgment about the content.

Found a possible error? Request a correction.